You are on page 1of 99

Uma Introdução ao R

http://translate.googleusercontent.com/translate_c?hl=pt-BR&ie=UTF-...

Uma Introdução ao R
Tabela de Conteúdos
Uma Introdução ao R Prefácio 1 Introdução e preliminares 1.1 R O ambiente 1,2 software e documentação relacionada 1,3 R e estatísticas 1,4 R eo sistema de janelas 1.5 Usando R interativamente Uma sessão introdutória 1,6 1,7 Obter ajuda com funções e características 1,8 comandos R, maiúsculas e minúsculas, etc Lembre-se 1,9 e correção dos comandos anteriores 1,10 executar comandos a partir de ou desviar a saída para um arquivo 1,11 permanência de dados e objetos de remoção Duas manipulações simples, números e vetores 2,1 Vetores e atribuição 2,2 aritmética Vector 2,3 gerar seqüências regulares 2,4 vetores lógicos 2,5 valores em falta 2,6 Personagem vetores Índice de 2,7 vetores; seleção e modificação de subconjuntos de um conjunto de dados 2,8 Outros tipos de objetos 3 Objetos, seus modos e atributos 3,1 atributos intrínsecos: modo e tempo 3.2 Alterando o comprimento de um objeto 3,3 obter e definir atributos 3,4 A classe de um objeto 4 e ordenada desordenadas fatores Um exemplo específico 4,1 4.2 A função tapply() e matrizes irregulares 4,3 fatores ordenada 5 matrizes e matrizes 5,1 Arrays 5,2 a indexação de matriz. Subseções de uma matriz 5,3 matrizes Índice 5.4 O array() função 5.4.1 vetores e aritmética mista matriz. A regra da reciclagem 5,5 exterior O produto de duas matrizes 5,6 transposição generalizada de uma matriz 5,7 instalações Matrix 5.7.1 A multiplicação de matrizes 5.7.2 equações lineares e inversão 5.7.3 Autovalores e autovetores 5.7.4 decomposição em valores singulares e determinantes 5.7.5 ajuste dos mínimos quadrados e decomposição QR 5,8 Formação matrizes particionadas, cbind() e rbind()

1 de 99

25/02/2011 10:36

Uma Introdução ao R

http://translate.googleusercontent.com/translate_c?hl=pt-BR&ie=UTF-...

5,9 concatenação A função, c() , com matrizes 5,10 tabelas de freqüência de fatores 6 listas e quadros de dados Listas de 6,1 6,2 Construir e modificar listas 6.2.1 Listas de concatenação 6,3 quadros de dados 6.3.1 Fazendo quadros de dados 6.3.2 attach() and detach() 6.3.3 Trabalhando com quadros de dados 6.3.4 Anexando listas arbitrárias 6.3.5 Gerenciando o caminho de pesquisa 7 Os dados de leitura de arquivos 7.1 O read.table() função 7.2 A scan() função 7,3 datasets Acessando builtin 7.3.1 Carregando dados a partir de R outros pacotes 7,4 Editando dados 8 As distribuições de probabilidade 8,1 R, um conjunto de quadros estatísticos 8,2 Examinando a distribuição de um conjunto de dados 8,3 e dois testes de amostra de um 9 Agrupamento, loops e execução condicional 9,1 expressões Agrupado 9,2 Instruções de controle 9.2.1 Execução condicional: if as declarações 9.2.2 execução repetitiva: for loops, repeat e while 10 Escrevendo suas próprias funções 10,1 exemplos simples 10,2 definir novos operadores binários 10,3 argumentos nomeados e padrões 10.4 A '...' argumento 10,5 atribuições dentro de funções 10,6 exemplos mais avançados 10.6.1 Os factores de eficiência em blocos 10.6.2 descartando todos os nomes em uma matriz impressa 10.6.3 integração numérica recursiva 10,7 Âmbito 10,8 Personalizando o ambiente 10,9 Classes, funções genéricas e orientação a objetos 11 modelos estatísticos em R 11,1 Definição de modelos estatísticos, fórmulas 11.1.1 Contrastes 11,2 modelos lineares 11,3 funções genéricas para extrair informações sobre o modelo 11.4 Análise de variância e um modelo de comparação 11.4.1 tabelas ANOVA 11,5 Atualizando modelos equipados 11,6 modelos lineares generalizados 11.6.1 Famílias 11.6.2 O glm() função 11,7 mínimos quadrados não-lineares e modelos de máxima verossimilhança 11.7.1 Método dos mínimos quadrados 11.7.2 máxima verossimilhança

2 de 99

25/02/2011 10:36

Uma Introdução ao R

http://translate.googleusercontent.com/translate_c?hl=pt-BR&ie=UTF-...

11,8 Alguns modelos não-standard 12 procedimentos Gráfica 12,1 alto nível comandos de plotagem 12.1.1 A plot() função 12.1.2 Resultados de dados multivariados 12.1.3 Artes gráficas 12.1.4 Argumentos para alto nível de plotagem funções 12,2 baixo nível de comandos de plotagem 12.2.1 anotação Matemática 12.2.2 fontes Hershey vetor 12,3 Interagindo com gráficos 12.4 Usando parâmetros gráficos 12.4.1 mudanças permanentes: O par() função 12.4.2 mudanças temporárias: Argumentos para funções gráficas 12,5 Graphics lista de parâmetros 12.5.1 Os elementos gráficos 12.5.2 eixos e marcas de escala 12.5.3 margens Figura 12.5.4 ambiente figura múltipla 12,6 drivers de dispositivos 12.6.1 diagramas PostScript para escrever documentos 12.6.2 múltiplos dispositivos gráficos 12,7 gráficos dinâmicos 13 Pacotes 13,1 pacotes Standard 13,2 pacotes de Contribuição e CRAN 13,3 Namespaces Apêndice sessão de amostra AA Apêndice B Invocando R B.1 R Invocando a partir da linha de comando B.2 Invocando R no Windows B.3 Invocando R no Mac OS X B.4 Script com R Apêndice C A linha de comando-editor Preliminares C.1 Edição de ações C.2 Editor de resumo de linha de comando C.3 Apêndice D Função e índice variável Apêndice E índice Concept Referências Apêndice F Seguinte: Prefácio , Precedente: (dir) , Up: (dir)

Uma Introdução ao R
Esta é uma introdução ao R ("GNU S"), uma linguagem e ambiente para computação estatística e gráficos. R é similar ao sistema S premiada, que foi desenvolvido nos Laboratórios Bell por John Chambers et al. Ele fornece uma ampla variedade de técnicas estatísticas e gráficas (modelagem linear e não linear, testes estatísticos, análise de séries temporais, classificação, agrupamento, ...). Este manual fornece informações sobre tipos de dados, elementos de programação, modelagem estatística e gráficos. A versão atual deste documento é 2.12.1 (2010/12/16).

3 de 99

25/02/2011 10:36

Uma Introdução ao R http://translate. ISBN 3-900051-12-7 Prefácio Introdução e preliminares Simples números manipulações e vetores Objetos Fatores Matrizes e matrizes Listas e quadros de dados Lendo dados de arquivos As distribuições de probabilidade Loops e execução condicional Escrever suas próprias funções Os modelos estatísticos em R Gráficos Pacotes A sessão de exemplo Invocando R A linha de comando-editor e variável índice de Função Conceito de índice Referências Seguinte: Introdução e preliminares . Anterior: Top . Fizemos uma série de pequenas alterações para refletir as diferenças entre os programas R e S. Comentários e correções são sempre bem vindos.. Gostaríamos de agradecer sinceramente a Bill Venables (e David Smith) para a concessão de permissão para distribuir esta versão modificada das notas. Por favor. endereço para correspondência e-mail para R-core@R-project.com/translate_c?hl=pt-BR&ie=UTF-. Smith quando da Universidade de Adelaide. Neste caso.googleusercontent. Introdução e preliminares Seguinte: manipulações simples números e vetores . e ampliou alguns dos materiais. Muitos usuários chegará a R principalmente para as suas instalações gráficas. Up: Top 1 Introdução e preliminares 4 de 99 25/02/2011 10:36 . Isto deve dar alguma familiaridade com o estilo de R sessões e mais importante feedback algum instante sobre o que realmente acontece. e por ser um defensor da R do caminho de volta. Up: Top Prefácio Esta introdução para R é derivado de um original conjunto de notas que descrevam o S-PLUS e ambientes S escrito em 1990-2 por Bill Venables e David M.org . Sugestões para o leitor A maioria dos novatos R começará com a sessão introdutória no Apêndice A. Anterior: Prefácio . desta forma.. gráficos sobre as instalações de gráficos pode ser lido em quase todo o tempo e não precisa esperar até que todas as seções anteriores foram digeridas.

Uma Introdução ao R

http://translate.googleusercontent.com/translate_c?hl=pt-BR&ie=UTF-...

O ambiente R Related software e documentação R e estatísticas R eo sistema de janelas Usando R interativamente Obter ajuda R comandos; maiúsculas e minúsculas etc Recall e correção dos comandos anteriores A execução de comandos de saída ou o desvio para um arquivo Dados permanência e removendo objetos Seguinte: software e documentação relacionada , Anterior: Introdução e preliminares , Up: Introdução e preliminares 1,1 O ambiente R R é um conjunto integrado de recursos de software para manipulação de dados, cálculo e exibição gráfica. Entre outras coisas, ele tem um tratamento eficaz de dados e instalação de armazenamento, um conjunto de operadores para cálculos em matrizes, matrizes em particular, um grande conjunto coerente e integrado de ferramentas de intermediário para a análise dos dados, facilidades gráficas para análise de dados e exibir diretamente no computador ou em cópia impressa e uma linguagem de programação bem desenvolvida, simples e eficaz (chamado `S '), que inclui condicionais, loops, funções definidas pelo usuário recursiva e facilidades de entrada e saída. (Na verdade a maioria das funções do sistema fornecidos são escritos na linguagem de S). O termo "ambiente" destina-se a caracterizá-lo como um sistema totalmente planejada e coerente, ao invés de uma acumulação gradual de ferramentas muito específicas e rígidas, como é frequentemente o caso com outros softwares de análise de dados. R é muito mais um veículo para desenvolver novos métodos de análise de dados interativa. Ele se desenvolveu rapidamente, e foi prorrogado por uma grande coleção de pacotes. No entanto, a maioria dos programas escritos em R são essencialmente efêmeros, escrito por uma única peça de análise de dados. Seguinte: R e estatísticas , Precedente: R ambiente A , Up: Introdução e preliminares 1,2 software e documentação relacionada R pode ser considerada como uma implementação da linguagem de S, que foi desenvolvido nos Laboratórios Bell por Rick Becker, John Chambers Wilks e Allan, e também forma a base dos sistemas S-P LUS. A evolução da linguagem é caracterizada por quatro livros por John Chambers e co-autores. Por R, a referência básica é o novo S Idioma: Um ambiente de programação para análise de dados e imagens por Richard A. Becker, M. e R. John Chambers Allan Wilks. As novas características da versão 1991 do S são abordados em Modelos Estatísticos em S editado por John Chambers M. e J. Trevor Hastie. Os métodos formais e classes do pacote são baseados em métodos daqueles descritos na programação com dados por John M. Chambers. Veja Referências , referências precisas.

5 de 99

25/02/2011 10:36

Uma Introdução ao R

http://translate.googleusercontent.com/translate_c?hl=pt-BR&ie=UTF-...

Há agora uma série de livros que descrevem como usar o R para análise de dados e estatísticas e documentação para o S / S-PLUS pode ser usado tipicamente com R, mantendo as diferenças entre as implementações S em mente. Consulte a documentação que existe para R? . Seguinte: R eo sistema de janelas , Precedente: software e documentação relacionada , Up: Introdução e preliminares 1,3 R e estatísticas Nossa introdução ao ambiente de R não mencionou as estatísticas, mas muitas pessoas usam R como um sistema de estatísticas. Nós preferimos pensar que de um ambiente no qual muitos clássicas e modernas técnicas estatísticas têm sido implementadas. Alguns destes são incorporados ao ambiente R base, mas muitos são oferecidos como pacotes. Há cerca de 25 pacotes fornecidos com R (chamada de "padrão" e "recomenda" pacotes) e muitos mais estão disponíveis através da família CRAN de sites da Internet (via http://CRAN.R-project.org ) e em outros lugares. Mais detalhes sobre os pacotes são dadas mais tarde (ver pacotes ). A maioria das estatísticas clássicas e muito mais nova metodologia está disponível para uso com R, mas os usuários podem precisar de ser preparado para fazer um pouco de trabalho para encontrá-lo. Há uma importante diferença de filosofia entre S (e, portanto, R) e os outros principais sistemas estatísticos. Em uma análise estatística S é normalmente feito como uma série de etapas, com resultados intermediários sendo armazenados nos objetos. Assim, enquanto a SAS e SPSS dará saída abundante de uma análise de regressão ou discriminante, R dará saída mínima e armazenar os resultados em um objeto adequado para posterior interrogatório por funções mais R. Próximo: Usando R interativamente , Precedente: R e estatísticas , Up: Introdução e preliminares 1,4 R eo sistema de janelas A maneira mais conveniente de usar R está em uma estação de trabalho gráfico com um sistema de janelas. Este guia é dirigido aos usuários que têm essa facilidade. Em particular, ocasionalmente se referem ao uso de R em um sistema de janelas X, embora a grande maioria do que é dito é de aplicação geral a qualquer aplicação do ambiente R. A maioria dos usuários acham necessário interagir diretamente com o sistema operacional em seu computador de vez em quando. Neste guia, principalmente discutir a interação com o sistema operacional em máquinas UNIX. Se você estiver executando o R no Windows ou Mac OS você vai precisar fazer alguns pequenos ajustes. Configurando uma estação de trabalho para tirar o máximo proveito dos recursos personalizáveis de R é um procedimento simples mas um pouco tedioso, e não será considerada mais aqui. Usuários em dificuldade deve procurar ajuda especializada local. Seguinte: Como obter ajuda , Precedente: R eo sistema de janelas , Up: Introdução e preliminares 1.5 Usando R interativamente Quando você usa o programa R emite um alerta quando se espera que os comandos de entrada. O aviso padrão é ' > ', que em UNIX pode ser o mesmo que a janela de comandos, e assim pode parecer que nada está acontecendo. No entanto, como veremos, é fácil de mudar para um R prompt diferente se desejar. Vamos supor que o shell do UNIX prompt é ' $ '. Ao utilizar o R no UNIX o procedimento sugerido para o primeiro é o seguinte:

6 de 99

25/02/2011 10:36

Uma Introdução ao R

http://translate.googleusercontent.com/translate_c?hl=pt-BR&ie=UTF-...

1. Criar um sub-diretório separado, dizem que o trabalho, para armazenar arquivos de dados em que você vai usar R para este problema. Este será o diretório de trabalho sempre que você usar R para este problema particular.
$ Mkdir work $ Cd work

2. Inicie o programa R com o comando
R $

3. Neste ponto R comandos podem ser emitidos (ver adiante). 4. Para encerrar o programa R, o comando é
> Q ()

Neste ponto, você será perguntado se deseja salvar os dados da sua sessão R. Em alguns sistemas, isso fará com que uma caixa de diálogo, e em outros que você irá receber um prompt para que você possa responder sim, não ou cancelar (uma abreviação de letra vai fazer) para salvar os dados antes de sair, sair sem salvar, ou retornar para a sessão R. Dados que é salvo estará disponível em futuras sessões R. outras sessões R são simples. 1. Fazer o trabalho do diretório de trabalho e iniciar o programa como antes:
$ Cd work R $

2. Use o programa R, que encerra com a q() o comando no final da sessão. Para usar o R no Windows o procedimento a seguir é basicamente o mesmo. Crie uma pasta como a pasta de trabalho, e definir que, no campo Iniciar Em seu atalho R. Em seguida, inicie R clicando duas vezes sobre o ícone. 1,6 Uma sessão introdutória Os leitores que quiserem ter uma idéia de R em um computador antes de prosseguir são fortemente aconselhados a trabalhar com a sessão introdutória dada em uma sessão de amostra . Seguinte: R comandos; maiúsculas e minúsculas etc , Anterior: Usando R interativamente , Up: Introdução e preliminares 1,7 Obter ajuda com funções e características R tem um mecanismo de ajuda inbuilt semelhante ao man facilidade de UNIX. Para obter mais informações sobre qualquer chamada função específica, por exemplo, solve , o comando é
> Ajuda (resolver)

Uma alternativa é
>? Resolver

Para um recurso especificado por caracteres especiais, o argumento deve ser colocado entre aspas simples ou duplas, tornando-se uma "cadeia de caracteres": Essa também é necessário para algumas palavras com significado sintático, incluindo if , for e function .
> Ajuda ("[[")

7 de 99

25/02/2011 10:36

Os exemplos em um tópico de ajuda pode normalmente ser executado por > Example (topic) A versões Windows do R ter outros sistemas de ajuda opcionais: use >? Ajuda para mais detalhes. de preferência.8 comandos R. com a restrição de que um nome deve começar com' . Se um comando não está completa no final de uma linha. ele é avaliado. Up: Introdução e preliminares 1. Nossa convenção é usar aspas duplas.start() é particularmente útil. maiúsculas e minúsculas.. ' o segundo personagem não deve ser um dígito. Os nomes são actualmente limitado a 256 bytes. começando com uma cancela (' # '). comandos elementares podem ser agrupadas em uma expressão composta por chaves (' { 'e' } '). R dará um padrão diferente pronta..com/translate_c?hl=pt-BR&ie=UTF-.start () que vai lançar um navegador da Web que permite que as páginas de ajuda para serem acessadas por hiperlinks. comandos Fundamental consistir em expressões e atribuições. O conjunto de símbolos que podem ser usados em nomes de R depende do sistema operacional e do país em que R está sendo executado (tecnicamente na localidade em uso). Na maioria das instalações de R ajuda está disponível em formato HTML. impressa (salvo se tornado invisível). Comentários podem ser colocados quase dois em qualquer lugar. Por exemplo. Os comandos são separados por um ponto e vírgula (' . '). que busca ainda funções disponíveis. por isso A e a são diferentes símbolos e remete para as diferentes variáveis. Anterior: Obtendo ajuda .search para mais detalhes e mais exemplos. Qualquer forma de aspas pode ser usado para escapar do outro. como na seqüência "It's important" . eo valor é perdido. etc Tecnicamente R é uma linguagem de expressão com uma sintaxe muito simples. por meio 8 de 99 25/02/2011 10:36 . O «motor e palavras-chave 'do link da pesquisa na página carregada pelo help. executando > Help. Seguinte: Recall e correção dos comandos anteriores . " e ' _ '. os pedidos de ajuda subseqüentes são enviadas para o sistema de ajuda baseado em HTML. O help. mas o resultado não é impresso automaticamente.Uma Introdução ao R http://translate. Pode ser uma ótima maneira de se orientar rapidamente e entender a amplitude do que R tem para oferecer. ' ou uma letra. É sensível como a maioria dos pacotes base UNIX. tudo até o fim da linha é um comentário .googleusercontent. isso inclui os caracteres acentuados) plus ' . pois é conceito contém uma lista de alto nível. Se uma expressão é dada como um comando. Normalmente todos os símbolos alfanuméricos são permitidos um (e em alguns países. ou por uma nova linha. e se inicia com ' . A cessão também avalia uma expressão e passa o valor para uma variável. >? Resolver Tentar ?help.search comando (em alternativa ?? ) permite procurar ajudar de várias formas. No UNIX.

eles podem ser executados a qualquer momento em uma sessão de R com o comando > Fonte ("commands. A capacidade de convocação e de edição em UNIX são altamente personalizáveis.googleusercontent.. Emacs Speaks Statistics) para trabalhar interativamente com R.R na obra diretório de trabalho. o cursor pode ser movido dentro do comando usando as teclas de seta horizontal. Up: Introdução e preliminares 1. O comando > Pia () restaura-lo para o console novamente.com/translate_c?hl=pt-BR&ie=UTF-. Você pode descobrir como fazer isso lendo o manual de entrada para a biblioteca readline. A função de sink . Precedente: R comandos.R") Para Fonte do Windows também está disponível no menu Arquivo. Nós geralmente omitem a continuação pronta e indicar a continuidade de recuo simples. matrizes de números. seqüências de caracteres. e os personagens podem ser removidos com a chave <DEL> ou adicionados com as outras teclas. Ver R e Emacs . maiúsculas e minúsculas etc .lis") irá desviar todas as saídas subseqüentes do console para um arquivo externo. Seguinte: Dados permanência e remoção de objetos .10 executar comandos a partir de ou desviar a saída para um arquivo Se os comandos quatro são armazenados em um arquivo externo. o editor de texto Emacs fornece mecanismos de apoio mais geral (por meio de ESS. > Pia ("record. Próximo: Executando comandos a partir de ou desviar a saída para um arquivo . record. Up: Introdução e preliminares Lembre-se 1. desta forma. As teclas de seta vertical no teclado pode ser usado para rolar para frente e para trás através de uma história de comando. Uma vez que o comando está localizado. + no segundo e subseqüentes linhas e continuar a ler a entrada até que o comando é sintaticamente completa.Uma Introdução ao R http://translate. funções ou estruturas mais gerais construídos a 9 de 99 25/02/2011 10:36 .. Esta pergunta pode ser alterada pelo usuário.9 e correção dos comandos anteriores De acordo com várias versões do UNIX e Windows.11 permanência de dados e objetos de remoção As entidades que R cria e manipula são conhecidos como objetos. R fornece um mecanismo para chamar e re-execução de comandos anteriores. Precedente: Recall e correção dos comandos anteriores . Anterior: A execução de comandos de saída ou o desvio para um arquivo . digamos commands. Como alternativa.lis. As linhas de comando digitada no console são limitados 3 a cerca de 4095 bytes (caracteres não). Mais detalhes são fornecidos mais tarde: ver a linha de comando-editor . Estas podem ser variáveis. Up: Introdução e preliminares 1.

7) Esta é uma declaração de atribuição usando a função c() que. Up: Top Duas manipulações simples. Se você indicar que você quer fazer isso. Rdata 5 no diretório atual. 3. Up: Simple números manipulações e vetores 2. O comando R objetos> () (Alternativamente. 21.4. Anterior: Introdução e preliminares . os objetos são criados e armazenados pelo nome (discutiremos esse processo na próxima sessão). tinta. Durante uma sessão I.c (10. 6.1 Vetores e atribuição R opera sobre estruturas de dados nomeado.googleusercontent. bar) Todos os objetos criados durante uma sessão de R pode ser armazenado permanentemente em um arquivo para uso em futuras sessões R. o associado do histórico dos comandos é recarregada. Seguinte: Objetos . que é uma entidade única.1. consistindo de cinco números. É bastante comum para objetos com nomes x e y a ser criado durante a análise.com/translate_c?hl=pt-BR&ie=UTF-.1. y.7. Recomenda-se que você deve usar separar diretórios de trabalho para as análises efectuadas com R. 5. números e vetores Vetores e atribuição aritmética Vector regular gerar seqüências Lógico vetores Os valores em falta Personagem vetores Índice de vetores Outros tipos de objetos Seguinte: Vector aritmética . partir de tais componentes.4.6. e as linhas de comando usado na sessão são salvos em um arquivo chamado.. anterior: Simple números manipulações e vetores . Para configurar um vetor denominado x . ou seja.Uma Introdução ao R http://translate. Para remover objetos da função rm está disponível: > Rm (x. 5. 6. Ao mesmo tempo. 6 10 de 99 25/02/2011 10:36 . digamos.6. neste contexto pode ter um número arbitrário de argumentos de vetor e cujo valor é um vetor tem concatenando seus argumentos finais até ao fim. A estrutura mais simples como é o vetor numérico. Quando R é iniciado na tarde do mesmo diretório que recarrega o espaço de trabalho a partir deste arquivo. os objetos são gravados em um arquivo chamado. use o comando R > X <. que consiste em uma coleção ordenada de números.. mas pode ser bastante difícil decidir o que pode ser quando as análises foram conduzidas várias no mesmo diretório. foo. 3. z. sucata. A coleção de objetos armazenados atualmente é chamado o espaço de trabalho. Rhistory. ls() ) pode ser usado para exibir os nomes dos (a maioria) os objetos que estão atualmente armazenados no R. No final de cada sessão R é-lhe dada a oportunidade de salvar todos os objetos disponíveis no momento. temp.4 e 21.4. Nomes como este são muitas vezes significativos no contexto de uma única análise. 10.

cos . que é a mesma sum(x)/length(x) .1. A tarefa ainda mais <> Y . caso em que as operações são realizadas elemento por elemento. Assim. 2*x 2. tan .. usando a evidente mudança de operador de atribuição.com/translate_c?hl=pt-BR&ie=UTF-. / e ^ para elevar a uma potência.2 aritmética Vector Vetores podem ser usados em expressões aritméticas. 5.4. a ' = operador pode ser usado como uma alternativa. 6..2 * x + y + 1 gera um novo vetor v de comprimento 11 construído pela soma. x) criaria um vetor y com 11 entradas composto de duas cópias de x com um zero no lugar do meio. log . Se não forem. com as atribuições acima do comando V <> .2 repetidas vezes. 6. Duas funções estatísticas são mean(x) que calcula a média da amostra. range é uma função cujo valor é um vetor de comprimento dois. max e min e selecionar o menor eo maior elementos de um vetor.6. sum(x) dá o total dos elementos em x .'). respectivamente.. Atribuição também pode ser feita usando a função assign() . pode ser pensado como um sintática atalho para isso. elemento por elemento. Vetores ocorrendo na mesma expressão não precisam ser todos do mesmo comprimento.googleusercontent. e 1 repetido 11 vezes. 5. e assim por diante.4. exp . Seguinte: regular gerar seqüências . a mesma atribuição pode ser feita usando > C (10.1. que consiste de dois personagens do < "(" menor que ") e" . agora. <. Uma maneira equivalente de fazer a mesma tarefa como acima está com: > Assign ("x". o valor é impresso e perdeu 7 . uma constante é simplesmente repetido. em uma expressão é tida como um vetor de comprimento um. Up: Simple números manipulações e vetores 2.4.c (x.7) -> x Se uma expressão é usada como um comando completo. Assim. sqrt . permanece inalterado). . isto é.Uma Introdução ao R http://translate.6. max(x)) . c (10. e var(x) que dá sum ((x-média (x)) ^ 2) / (comprimento (x) -1) 11 de 99 25/02/2011 10:36 . c(min(x). 21. se tivéssemos que usar o comando > 1 / x os inversos dos cinco valores seriam impressas no terminal (eo valor de x ..4."(" menos ") que ocorrem estritamente lado a lado e` pontos 'para o objeto que recebe o valor da expressão. Precedente: Vetores e atribuição . e prod(x) o seu produto. que ocorre na expressão. Na maioria dos contextos. 3. vetores mais curtos na expressão são recicladas quantas vezes necessário (talvez fracionada). todos têm seu significado usual. Observe que o operador de atribuição (' <. length(x) é o número de elementos em x . y repetida apenas uma vez. é claro.7)) O operador de costume. * . 3. 21. 0. Além de todas as funções aritméticas comuns estão disponíveis. até que elas coincidam com o comprimento do maior vetor. o valor da expressão é um vetor com o mesmo comprimento que o maior vetor. sin . Um número que ocorre por si só. Os operadores aritméticos elementares são os habituais + . Então. Atribuições também pode ser feita em outra direção. Em especial.

Por exemplo > Seq (-5. se houver. Internamente. mesmo se eles tiverem vários vetores. caso em que a ordem em que aparecem é irrelevante. Os primeiros dois parâmetros pode ser chamado from= valor e to= valor. fonte de uma parte explícita complexo. to=30) e seq(to=30. Parâmetros para seq() . 5. .Uma Introdução ao R http://translate. e para muitas funções R outro. -4... reais ou mesmo complexos..6. assim seq(1. porém existem outras instalações de classificação mais flexível disponível (veja a order() ou sort. . Assim sqrt (-17) dará NaN e uma advertência. -4.8.. A construção 30:1 pode ser usado para gerar uma seqüência para trás. Os primeiros dois argumentos. Coloque n <.0. por exemplo 2*1:15 é o vetor c(2. por =. Se o argumento para var() é um n-por-p-valor da matriz é um sub-p-p covariância da amostra tem por matriz a respeito das linhas como independente variada amostra de vetores-p..list() que produzem uma permutação para fazer a classificação) . 30) . O operador dois pontos tem alta prioridade dentro de uma expressão. retorna um vetor do mesmo tamanho de x com os elementos dispostos em ordem crescente. 29. regular gerar seqüências Seguinte: vetores lógicos .0) . Os próximos dois parâmetros para seq() pode ser chamado by= valor e length= valor.. Para a maioria dos efeitos que o usuário não se preocupa se os "números" em um vetor numérico são inteiros. Por exemplo 1:30 é o vetor c(1. O valor máximo e mínimo de funções paralelas pmax e pmin retornar um vetor (de comprimento igual ao seu maior argumento) que contém em cada elemento o maior eo menor) elemento (em que a posição em qualquer um dos vetores de entrada. Do mesmo modo 12 de 99 25/02/2011 10:36 . 30) .. especificar o início eo fim da seqüência. o padrão by=1 é assumido. 2. ou variância da amostra..6. mas sqrt (-17 0 i) fará os cálculos de números complexos. 5.10 e comparar as seqüências 1:n-1 e 1:(n-1) . os cálculos são feitos com precisão dupla números reais ou números de precisão dupla complexo se os dados de entrada são complexas. Up: manipulações simples números e vetores Geração de 2.. . sort(x) Para trabalhar com números complexos. 4. Ela tem cinco argumentos.. Isso é seq(2.. 28.3 seqüências regulares R tem um número de instalações para a geração de seqüências comumente utilizado de números. seq(from=1. Se nenhum desses for dada. 4.10) é o mesmo vetor como 2:10 .30) . só algumas das quais podem ser especificados em qualquer uma chamada. Precedente: aritmética Vector . from=1) são todos iguais como 1:30 . por isso. 2) -> s3 gera em s3 o vetor c(-5. 4.8. também pode ser dada em forma de nome. A função seq() é um mecanismo mais geral para a geração de seqüências.googleusercontent. que especifica um tamanho de passo e um comprimento para a seqüência respectivamente. Note-se que max e min e selecionar o menor eo maior valores em seus argumentos. e se estes são os dois únicos argumentos que apresenta o resultado é o mesmo que o operador dois pontos.com/translate_c?hl=pt-BR&ie=UTF-.

se c1 e c2 são expressões lógicas. portanto. que se for utilizado deve ser o único parâmetro. > S4 <. Os dois primeiros são abreviadas como T e F .googleusercontent. A função está relacionada rep() que pode ser usado para replicar um objeto de diversas maneiras complicadas. FALSE se tornando 0 e TRUE se tornar 1 . A função is. atribuindo a ela o valor especial NA . Precedente: regular gerar seqüências . >= . ou a seqüência vazia se o vetor está vazia (como pode ser ). os componentes de um vetor não pode ser completamente conhecida. por =. Lógico vetores podem ser usados na aritmética o ) comum. a partir =. Precedente: vetores lógicos . você deve sempre usar TRUE e FALSE . por padrão. Seguinte: Os valores em falta . Além disso. Lógico vetores são gerados por condições. mas não são palavras reservadas e. não está disponível. Portanto. Up: manipulações simples números e vetores 2.rep (x. A forma mais simples é > <S5 . Note no entanto que T e F são apenas as variáveis que são definidas para TRUE e FALSE . respectivamente. Up: Simple números manipulações e vetores 2.na(x) dá um vetor lógico do mesmo tamanho de x com o valor TRUE se e somente se o elemento correspondente em x é NA . FALSE . R permite a manipulação de quantidades de lógica. > .. vezes = 5) que vai colocar cinco cópias de x fim-de-final em s5 .x> 13 define temp como um vetor de mesmo comprimento que x ..5 valores em falta Em alguns casos. No entanto. Próxima: Personagem vetores . 2. . Quando um elemento ou o valor é "não disponível" ou um "valor faltando" no sentido estatístico. c1 & c2 é a intersecção (" ". Os elementos de um vetor lógico pode ter os valores TRUE . veja abaixo). qualquer operação realizada sobre um NA torna-se um NA . existem situações onde os vetores lógicos e seus homólogos coagido numéricos não são equivalentes. veja na próxima subseção.Uma Introdução ao R http://translate. O quinto parâmetro pode ser nomeado along= vetor. 2) gera o mesmo vetor em s4 . cada = 5) que se repete cada elemento x cinco vezes antes de avançar para a próxima. e cria uma seqüência de 1. e !c1 é a negação de c1 . Por exemplo <Temp> . length( vetor ) .5. <= . c1 | c2 e) é a sua união (" u".4 vetores lógicos Bem como vetores numéricos. por exemplo. Outra versão é útil <> S6 .. 13 de 99 25/02/2011 10:36 . em seguida. == para a igualdade exata e != para a desigualdade. A motivação para esta regra é simplesmente que se a especificação de uma operação é incompleta. um lugar dentro de um vetor pode ser reservado para ela.rep (x. com valores FALSE correspondentes aos elementos de x em que a condição não for cumprida e TRUE onde ela está. caso em que são coagidos a vetores numéricos. e NA (para "não disponível".com/translate_c?hl=pt-BR&ie=UTF-.. Os operadores lógicos são < . Em geral.seq (length = 51. pode ser substituído pelo usuário. portanto. o resultado não pode ser conhecido e..

Para diferenciá-las. Por exemplo > <Laboratórios . possivelmente vazio.Inf que ambos dão NaN desde que o resultado não pode ser definido de forma sensata. indecidível. Note que existe um segundo tipo de "desaparecidos" os valores que são produzidos por computação numérica.na(xx) é TRUE tanto para NA e NaN valores. is. "Y4". usando \ como caracter de escape. exemplos de uso vão surgir com frequência.nan(xx) só é TRUE para NaN s. "X3". Personagem vetores podem ser concatenados em um vetor pelo c() função.c (1:3. As cadeias de caracteres são digitados ou correspondência (double " ) ou simples ( ' ) aspas. às vezes impresso como <NA> vetores de caracteres quando são impressas sem aspas. isto é. a chamada Not a Number. o que muda é a cadeia. "X9". 14 de 99 25/02/2011 10:36 . e dentro de aspas duplas " está inscrita como \" .. Sempre que necessário.googleusercontent. Os valores em falta são. "X5". NaN . Em resumo. Outras seqüências de escape são úteis \n nova linha. valores. Exemplos são > 0 / 0 ou > Inf . "Y8". eles são indicados por uma seqüência de caracteres delimitados pelo caractere aspas duplas. mas são impressos usando aspas duplas (ou às vezes sem as aspas). \t . Assim x == NA é um vetor de mesmo comprimento que x todos cujos valores são NA . "X7". da mesma forma que seriam se fossem impressas. <ind . assim c("X". 8 "Y") é repetido cinco vezes para igualar a seqüência de 1:10 . dado entre os argumentos são coagidos a cadeias de caracteres no modo evidente. is. > Z <. Anterior: Os valores em falta . por exemplo. etiquetas parcela. Qualquer número. NA). mas um marcador para uma quantidade que não está disponível. assim \\ é entrou e impressos como \\ . portanto. "Y10") Note particularmente que a reciclagem de listas curtas acontece aqui também.. "Y2". guia e \b . backspace-ver? Cotações para uma lista completa. "New iteration results" .pasta (c ("X".com/translate_c?hl=pt-BR&ie=UTF-. Seguinte: Índice de vetores . por exemplo. O paste() função recebe um número arbitrário de argumentos e concatena-los um a um em cadeias de caracteres. 1:10. como a expressão lógica em si é incompleta e. mas isso pode ser alterado pelo parâmetro nomeado.Uma Introdução ao R http://translate.is. "x-values" . setembro = "") faz labs para o vetor de caracteres c ("X1". Up: Simple números manipulações e vetores 2. Os argumentos são separados por padrão no resultado por um único caractere em branco. Eles usam seqüências de escape estilo-C.6 Personagem vetores Personagem quantidades e vetores de caracteres são utilizados freqüentemente em R.na (z) Observe que a expressão lógica x == NA é muito diferente de is. sep= string. "Y").na(x) desde NA não é realmente um valor. "Y6".

x [! Is.. no resultado. Neste caso. y será menor que x .. <> Fruta . vetores Esse índice pode ser qualquer um dos quatro tipos distintos.2. "maçã". não de x . 1.c (5. "banana". "x" repetido quatro vezes. 20) > Nomes (fruta) <. Neste caso. Um vetor de seqüências de caracteres. Esta possibilidade só se aplica quando um objeto tem um names de atributo para identificar seus componentes. length(x) }. Esse índice vetor uma especifica os valores a serem excluídos e não incluídos. Note que se x tem valores em falta. um sub-vetor do vetor de nomes podem ser utilizados da mesma forma como os rótulos positivos integral no item 2 mais acima.. qualquer expressão que equivale a um vetor pode ter subconjuntos dos seus elementos igualmente selecionadas anexando um vetor de índice entre colchetes imediatamente após a expressão.2. Por exemplo. O vetor de índice pode ser de qualquer tamanho. 3. Um vetor de quantidades positivas integral.(1:5)] dá y todos. os tempos = 4)] (Uma coisa improvável certo a fazer) produz um vetor de caracteres de tamanho 16 que consiste em "x". 2.7 vetores. "y") [rep (c (1.c ("laranja". Um vetor lógico. Por exemplo <> Y . o índice do vetor deve ser do mesmo comprimento que o vetor a partir da qual os elementos devem ser selecionados. "y". Assim <> Y . Seguinte: Outros tipos de objetos .. x[6] é o sexto componente de x e > X [01:10] seleciona os 10 primeiros elementos de x (assumindo que length(x) não é inferior a 10).x [. 2. seleção e modificação de subconjuntos de um conjunto de dados Subconjuntos de elementos de um vetor pode ser selecionado por meio do acréscimo do nome do vetor um vetor de índice entre colchetes. Um vetor de quantidades negativas integral. "pêssego") > <Almoço . mas os cinco primeiros elementos de x . 1. "laranja")] frutas 15 de 99 25/02/2011 10:36 . Valores correspondentes a TRUE no vetor de índice são selecionados e os correspondentes à FALSE são omitidos.1). eo resultado é do mesmo comprimento que o vetor de índice.Uma Introdução ao R http://translate..com/translate_c?hl=pt-BR&ie=UTF-. Neste caso. Os elementos correspondentes do vetor são selecionadas e concatenadas. Up: manipulações simples números e vetores Índice de 2. Também > C ("x". anterior: Personagem vetores . os valores no vetor de índice deve estar no conjunto {1. Mais geral.na (x)) & x> 0] -> z cria um objeto z e lugares em que os valores do vetor x+1 para o qual o valor correspondente em x era ao mesmo tempo não falta e positiva. 4.[c ("maçã". nessa ordem. Também > (X +1) [(! Is. .na (x)] cria (ou recria) um objeto y que conterá os valores em falta. 10. na mesma ordem do.googleusercontent. "y".

na qual as colunas podem ser de diferentes tipos. O vetor atribuído deve corresponder ao tamanho do vetor de índice. Esta opção é particularmente útil em conexão com os quadros de dados. Up: Simple números manipulações e vetores 2. seus modos e atributos O modo de atributos intrínsecos e comprimento A mudança no comprimento de um objeto Obter e definir atributos A classe de um objeto 16 de 99 25/02/2011 10:36 .com/translate_c?hl=pt-BR&ie=UTF-. Por exemplo > X [is. Up: Top 3 Objetos. mais geralmente arrays são multi-dimensional de vetores de generalizações.8 Outros tipos de objetos Vetores são o tipo mais importante do objeto em R. A expressão deve ser da forma vector[ index_vector ] como tendo uma expressão arbitrária no lugar do nome do vetor não faz muito sentido aqui. A vantagem é que os nomes alfanuméricos são muitas vezes mais fácil de lembrar que os índices numéricos.. funções são objetos em R que pode ser armazenado em espaço de trabalho do projeto.. Precedente: números de simples manipulações e vetores . como veremos mais tarde.0 substitui os valores em falta em x por zeros e > Y [y <0] <--y [y <0] tem o mesmo efeito que > Y <. quadros de dados são. mas com (possivelmente) as duas variáveis numéricas e categóricas. caso em que a operação de atribuição é realizada apenas sobre os elementos do vetor. Seguinte: Fatores . Veja quadros de dados . que vamos encontrar mais formalmente nas seções posteriores.googleusercontent. listas são uma forma geral de vetor no qual os vários elementos não precisam ser do mesmo tipo. Na verdade. fatores fornecem maneiras compacto para manipular os dados categóricos.abs (y) Anterior: Índice de vetores . As listas oferecem um modo conveniente para retornar os resultados de um cálculo estatístico. Isso fornece uma maneira simples e conveniente para estender R. Muitas experiências são mais bem descrito por quadros de dados: os tratamentos são categóricos. Veja listas . Veja Fatores . como as estruturas da matriz. e no caso de um vetor de índice lógico que deve voltar a ser o mesmo comprimento que o vetor é a indexação. Veja matrizes e matrizes . eles são vetores que podem ser indexados por dois ou mais índices e será impresso de maneira especial. mas existem muitas outras.Uma Introdução ao R http://translate. mas a resposta é numérica.na (x)] <. Veja escrever suas próprias funções . Pense de quadros de dados como matrizes «dados» com uma linha por unidade de observação. matrizes ou. Uma expressão indexada também pode aparecer no fim de recepção de uma cessão. e muitas vezes são eles mesmos vetores ou listas.

O leitor deve consultar os arquivos de ajuda diferentes para se familiarizar com eles. Outras propriedades de um objeto são normalmente prestados por attributes( objeto ) .as. ou para investir um objeto com algum outro atributo que não pode já possuir. Listas são conhecidas como "recursivo" ao invés de estruturas atômicas desde que seus componentes possam ser eles próprios listas em seu próprio direito. numérica 9 . com > Z <. ou cru.googleusercontent. ou seja. Por exemplo. numérico. Por exemplo. 11 Existe uma grande coleção de funções da forma as. Exemplos são os vetores de valores numéricos (real) ou complexos. lógica e matérias-primas. Devido a isso. "1". a seqüência de vetores de caracteres vazia é listada como character(0) eo vetor numérica vazia como numeric(0) .as.1 atributos intrínsecos: modo e tempo As entidades R opera em são tecnicamente conhecidos como objetos.com/translate_c?hl=pt-BR&ie=UTF-... consulte Como obter e definir atributos . Precedente: Objetos . "2".integer (dígitos) Agora d e z são os mesmos. o modo e tempo são também chamados de "atributos intrínsecos" de um objeto. individualmente.. Up: Objetos 3. R serve para mudanças de modo quase em qualquer lugar que poderia ser considerado razoável para o fazer. se z é um vetor complexo de comprimento 100. O recursiva outras estruturas são os de função do modo de expressão. A coerção mais ou mudança de modo. Estes são conhecidos como "atômico" estruturas desde os seus componentes são todos do mesmo tipo. que são de modo lista. exceto indiretamente quando discutimos fórmulas usadas com modelagem em R. Estas são seqüências ordenadas de objetos que. qualquer dado vetor deve ser inequívoca.character (z) após o qual digits é o vetor de caracteres c("0". Seguinte: A mudança no comprimento de um objeto .Uma Introdução ao R http://translate. Pelo modo de um objeto que significa que o tipo básico de seus componentes fundamentais. Este é um caso especial de uma "propriedade" de um objeto.00:09 poderíamos colocar dígitos> <. Por exemplo. natureza. Outra propriedade de cada objeto é o seu comprimento. mas na verdade existem vários tipos de NA ). pode ser de qualquer modo. ou modo.. As funções mode( objeto ) e length( objeto ) pode ser usada para descobrir o modo e tempo de qualquer estrutura definida 10 . Note-se que um vetor pode ser vazio e ainda ter um modo.. quer lógico. . Expressões como objetos fazem parte avançada de R que não serão discutidos neste guia. algo () para qualquer coerção de um modo para outro. então em uma expressão mode(z) é a seqüência de caracteres "complex" e length(z) é 100 . Vetores devem ter seus valores todos do mesmo modo. 17 de 99 25/02/2011 10:36 . vetores de valores lógicos e vectores de cadeias de caracteres. R também opera em objetos listas de chamada. de caráter complexo. "9") . (A aparente única excepção a esta regra é a "especial" o valor listado como NA para as quantidades não estão disponíveis. complexo. As funções são os objetos que fazem parte do sistema R junto com o usuário similar funções escritas. que serão discutidos em detalhe mais tarde. reconstrói o vetor numérico novamente: > D <. Assim. (e algumas em que não possa ser).

> Comprimento (alfa) <.. Up: Objetos 3. Assim > E [3] <.3 obter e definir atributos A função de attributes( objeto ) retorna uma lista de todos os não-atributos intrínsecos atualmente definidas para esse objeto. Seguinte: A classe de um objeto . A função attr( objeto . simplesmente.10) R permite tratar z . é muito importante. dando-lhe um valor de índice fora do intervalo anterior. nome ) pode ser usado para selecionar um atributo específico. Este ajuste automático do comprimento de um objeto é usado com freqüência. desde o modo do componente adicional (s) concorda com o modo do objeto em primeiro lugar.googleusercontent. no scan() função para a entrada.Uma Introdução ao R http://translate.) Inversamente para truncar o tamanho de um objeto requer apenas uma atribuição para fazê-lo. entretanto. Por exemplo > Attr (z. mesmo com o índice. 18 de 99 25/02/2011 10:36 . > <. Por exemplo > E <. e assim por diante. como se fosse um-por-10 da matriz 10.numérico () faz e uma estrutura de vetor vazio de modo numérico. Seguinte: Como obter e definir atributos .17 faz agora e um vetor de comprimento 3. Up: Objetos 3.c (10. Isso se aplica a qualquer estrutura de todos. para associar a criação de uma data ou um operador com um objeto R. Depois que um objeto de qualquer tamanho. novos componentes podem ser adicionados a ele.. O conceito.) Podemos então manter apenas os três primeiros valores. Quando ele é usado no lado esquerdo de uma atribuição que pode ser usado para associar um novo atributo com o objeto ou alterar um já existente. (Veja o scan () função .2 Alterando o comprimento de um objeto Um objeto "vazio" pode ainda ter um modo. que são neste momento os dois NA ). da mesma forma. por exemplo. Alguns cuidados devem ser tomados quando atribuir ou excluir atributos pois eles são uma parte integrante do sistema de objetos usados em R. Anterior: O modo de atributos intrínsecos e comprimento . Do mesmo modo character() é um vetor de caracteres vazia. exceto em circunstâncias muito especial quando algum novo atributo está sendo criado para algum propósito particular.3 e vetores pode ser estendido (por valores em falta).com/translate_c?hl=pt-BR&ie=UTF-. Portanto. Essas funções são raramente utilizadas. "dim") <. por exemplo. é claro.Alfa alfa [2 * 01:05] torna um objeto de comprimento 5 que compreende apenas os componentes antigos. foi criado. se alpha é um objeto de comprimento 10. Anterior: Mudando o comprimento de um objeto . (Os índices de idade não são mantidas. (os dois primeiros componentes.

temos uma amostra de 30 auditores fiscais de todos os estados e territórios da Austrália 13 e seu estado de origem individual é especificado por um vetor de caracteres de mnemônicos Estado como <> Estado . R fornece tanto desordenada e fatores de ordem. "sa". Objetos 3.. "array" . "Vic". ele será impresso em uma determinada maneira.frame" . "acto") Observe que no caso de um vetor de caracteres ". mas é quando você está aprendendo a entrar em acordo com a idéia de classe e funções genéricas. "qld".c ("tas". "NT". por exemplo. funções genéricas e as aulas serão discutidas mais adiante na orientação a objeto . a plot() função irá exibi-lo graficamente em uma determinada maneira.com/translate_c?hl=pt-BR&ie=UTF-. "NSW". e outros chamados funções genéricas como o summary() vai reagir a isso como um argumento de uma forma sensível a sua classe. se winter tem a classe "data. Enquanto o real "aplicação" de fatores é com as fórmulas do modelo (ver Contrastes ).1 Um exemplo específico Suponha. "wa". que é um pouco como uma matriz. por exemplo "numeric" . "character" ou "list" . enquanto unclass> (Inverno) irá imprimi-lo como uma lista comum. "NSW".Uma Introdução ao R http://translate. 4. se um objeto tem classe "data.factor (estado) 19 de 99 25/02/2011 10:36 . "qld". Anterior: Introdução e definição de atributos Up:.frame" . classificado" significa classificados em ordem alfabética. nós aqui olhar para um exemplo específico.4 A classe de um objeto Todos os objetos em P tem uma classe. Inverno> será impresso em formulário de dados do quadro. Para vetores simples. "sa".frame" são outros valores possíveis. "NSW". "factor" e "data. "Vic". "NT". Seguinte: matrizes e matrizes . "Vic". "Sa". "tas". relatado pela função de class . "qld". em seguida. "Sa". Up: Top 4 fatores ordenadas e desordenadas Um fator é um vetor de objeto usado para especificar uma classificação discreta (agrupamento) dos componentes de outros vetores de mesmo comprimento. "NSW". "wa". Um fator é igualmente criado usando o factor() função: > <Statef . "acto".. Um atributo especial. mas apenas momentaneamente. "wa". Por exemplo. este é apenas o modo. Somente em situações especiais. mas "matrix" . conhecida como a classe do objeto é usado para permitir um estilo de objeto orientado 12 de programação em R. "NSW". use a função unclass() . "Vic". "NSW". "wa". Por exemplo. "Vic". Para remover temporariamente os efeitos da classe. Precedente: Objetos . "qld". "Qld". "logical" .googleusercontent. em vez que você precisa para usar este recurso.

statef stderr) e os valores calculados são então incster> ato sa nt nsw qld tas wa vic 1.333 55. 58. aqui statef 14 . O resultado é uma estrutura do mesmo comprimento que os níveis de atributo do elemento que contém os resultados.600 55. 42. tal função é muito simples de uma linha. média) dando um vetor de meios com os componentes marcados pelos níveis ato sa nt nsw qld tas wa vic 44.c (60.000 52.6575 20 de 99 25/02/2011 10:36 . O print() função manipula fatores um pouco diferente de outros objetos: statef> [1] sa tas qld nsw nsw wa wa nt qld vic vic nsw qld qld sa [16] tas sa nt wa vic qld nsw nsw wa nsw ato sa ato Vic Níveis: nt nsw ato qld tas sa wa vic Para descobrir os níveis de um fator a função de levels() pode ser usado. 69. 62. 43) Para calcular a média da amostra de renda para cada estado agora podemos usar a função especial tapply() : > Incmeans <. Para isso. 48. para cada grupo de componentes do primeiro argumento. Como não há uma função embutida var() para calcular a variância da amostra. 59. 58. 40.2 A função tapply() e matrizes irregulares Para continuar o exemplo anterior. 54. como se fossem as estruturas do vetor separados . aqui mean() . "nsw" nt "qld" sa "" tas "vic" wa " O Tapply função () e matrizes irregulares fatores ordenada Seguinte: fatores ordenada . definidos pelos níveis do segundo componente. 60.5 4.Tapply (rendas. 56. 64.7386 0. 65. indicada pelo serviço: > <Stderr . 52.function (x) sqrt (var (x) / comprimento (x)) (Funções de escrita será considerada mais tarde. Precedente: Fatores .Uma Introdução ao R http://translate.. O leitor deve consultar o documento de ajuda para mais detalhes.250 A função tapply() é usada para aplicar uma função.3102 4. 49. 48.googleusercontent.. os erros-padrão são calculados por <Incster> .500 57. 49. 61.244 2. e neste caso era desnecessária.Tapply (rendas. em escrever suas próprias funções . 61.1061 2.500 53. 46. > Níveis (statef) [1] "acto". 46. Up: Fatores 4. 61. 49. 51. aqui incomes . visto que R tem também uma função embutida sd() ). 59. suponha que temos os rendimentos dos auditores fiscais num outro vector (em unidades suficientemente grande de dinheiro) <> Renda . 41.500 56. 61.5 4. precisamos escrever uma função de R para calcular o erro padrão para qualquer vector dado.5 5.com/translate_c?hl=pt-BR&ie=UTF-. Depois desta atribuição.000 60. 70. Suponha ainda que precisávamos para calcular o desvio padrão da renda do estado significa. statef.

Como um exercício. Quando os tamanhos das subclasses são todos os indexação o mesmo pode ser feito de modo implícito e muito mais eficiente. No entanto. uma vez que os tamanhos das subclasses são possivelmente irregular. mas o contraste gerado por eles no ajuste de modelos lineares são diferentes. marcado pela levels atributo do fator. você pode importar para encontrar os habituais limites de confiança de 95% para a média no estado de rendimentos. por exemplo numérico. e em particular o caso especial de matrizes.Uma Introdução ao R http://translate. Seguinte: Listas e quadros de dados . Precedente: matrizes e matrizes . R permite instalações simples para a criação e manipulação de matrizes. Up: matrizes e matrizes 5. poderíamos querer dividir os contabilistas fiscais por estado e sexo. ou na ordem em que foram especificados para factor se eles fossem especificados explicitamente. Para a maioria dos efeitos que a única diferença entre os fatores de ordenados e não ordenados é que os primeiros são impressos mostrando a ordem dos níveis. A função é aplicada a cada um desses grupos individualmente.3 fatores ordenada Os níveis dos fatores são armazenados em ordem alfabética.. O valor é um vetor de resultados da função. O ordered() função cria tais fatores ordenados mas de resto é idêntico ao factor . Up: Fatores 4. correspondentes às entradas distintas no fator. simples (apenas um fator) que acontece pode ser pensado como se segue.googleusercontent.com/translate_c?hl=pt-BR&ie=UTF-. neste caso. como podemos ver na próxima seção. Para fazer isso você poderia usar tapply() mais uma vez com o length() função para localizar os tamanhos de amostra e do qt() função para localizar os pontos de percentagem do adequado t-distribuições. Precedente: Fatores . Se o seu comprimento é k. (Você também pode investigar instalações de P para os testes-t). Os valores do vetor são coletados em grupos. então a 21 de 99 25/02/2011 10:36 .1 Arrays Uma matriz pode ser considerada como uma coleção multiplicar subscrita de entradas de dados. A dimensão do vetor é um vetor de inteiros não-negativos. A combinação de um vetor e um fator de rotulagem é um exemplo de que às vezes é chamada de matriz irregular.. Às vezes os níveis terão uma ordem natural que queremos gravar e queremos que a nossa análise estatística para fazer uso. A função tapply() também pode ser usado para tratar mais complicado indexação de um vetor por várias categorias. Anterior: A função Tapply () e matrizes irregulares . Up: Top 5 matrizes e matrizes Matrizes indexação de matriz Índice de matrizes A função Array () O produto externo das duas matrizes Generalizado transposição de uma matriz Facilidades Matrix Formando matrizes particionadas A função de concatenação c () com arrays tabelas de freqüência de fatores Em seguida: Matriz de indexação . Por exemplo.

digamos Z . Os valores no vetor de dados fornecem os valores da matriz na mesma ordem em que iria ocorrer em Fortran.2]) nessa ordem. toda a gama de subscrição que for tomada. Um vetor pode ser usado por R como uma matriz somente se ele tiver um vetor de dimensão como o seu atributo dim.100) lhe confere o atributo dim que permite que ele seja tratado como um "3 by 5 por 100 matriz. por exemplo. um [2. a[2. como veremos em A matriz () função . a [2. Outras funções.1..com/translate_c?hl=pt-BR&ie=UTF-..2]. Mais genericamente. é c(3. em seguida.. neste caso o vetor de dimensão é ignorada.1]. se o vetor de dimensão para uma matriz.2) eo vetor de dados contendo os valores c (a [2. anterior: a indexação de matriz . Por exemplo. Continuando o exemplo anterior.] é um 4 * 2 matriz com a dimensão do vetor c(4. o vetor de dimensão pode ser referenciado explicitamente como dim(Z) (em ambos os lados de uma atribuição). Para qualquer matriz. no entanto.4. Seguinte: Índice de matrizes .1. a[2. Além disso. Suponha. então há 3 * 4 * 2 = 24 entradas em a vetor de dados e os mantém na ordem a[1. a [2. diz a .3. Up: matrizes e matrizes 5.1].2].4. a [2. a [2..2.1]. A atribuição > Dim (z) <. se um nome de matriz é dado com apenas um índice ou um vetor de índice. como estamos proximos discutir.] representa a matriz inteira. a[.2) .1.4. tais como matrix() e array() estão disponíveis para simples e mais natural atribuições de quem. Anterior: Matrizes .1. separados por vírgulas. Subseções de uma matriz Os elementos individuais de uma matriz pode ser referenciado por dar o nome da matriz seguido pelos subscritos entre colchetes.. em seguida. os valores correspondentes do vetor de dados só são utilizadas. mas também uma matriz. Índice de matrizes A função Array () Seguinte: A função Array () . a[3. uma matriz é um array de 2 dimensões. mas as exceções podem causar confusão.2.4.3. por exemplo. Matrizes podem ser unidimensionais: matrizes deste tipo são normalmente tratados da mesma forma como vetores (incluindo a imprimir). Este não é o caso. matriz é k-dimensional. Up: matrizes e matrizes 22 de 99 25/02/2011 10:36 .4.1].c (3. que é "grande encomenda de coluna". em substituição de índices. no entanto.. as subseções de uma matriz pode ser especificado. a [2. .2] .googleusercontent.1].1].Uma Introdução ao R http://translate. a [2.2 a indexação de matriz. que é o mesmo que omitir a totalmente subscritos e usar a só. se qualquer posição do índice é dado um vetor de índice de vazios. dando uma seqüência de vetores de índice. a[2.5.2].2].. se o único índice não é um vetor. com o primeiro subscrito mais rápidos e mais lentos subscrito passado. z é um vetor de 1500 elementos. As dimensões são indexados a partir de um até os valores indicados no vetor de dimensão.

[4].1] como uma estrutura de vetor. b) > Xv <. Um exemplo da matriz torna o processo claro. 3 7 11 15 19 [4]. [1].. 4 8 12 16 20 > I <. [1]. um índice da matriz pode ser dada constituído por duas colunas e tantas linhas. c = dim (3. 2 2 [3]. como no exemplo a seguir. 0 7 11 15 19 [4].2)) > I # i é uma matriz 3 por 2 índice. > X <.2] e X[3.3:1). XV) Para construir a matriz de incidência. As entradas no índice da matriz são os índices de linha e coluna para a matriz duplamente indexados.matriz (c (1:3. temos uma matriz de 4 por 5 X e queremos fazer o seguinte: Extrair elementos X[1. ou extrair uma coleção irregular como um vetor. [3]. Suponha ainda existem n parcelas no experimento. X[2. uma matriz pode ser usada com um único índice da matriz seja para atribuir um vetor de quantidades para uma coleção irregular de elementos do array.5)) # Gera uma matriz de > X . 4 8 12 16 20 > 4 por 5.3] . Suponha.cbind (Xb. Como um exemplo menos trivial. > X . Nós poderíamos proceder da seguinte forma: > Xb <.matriz (0.matriz (0. c = dim (4. nós poderíamos usar > N <.0 # Substitua esses elementos zeros. [4].cbind (1: n. e Substituir essas entradas na matriz X por zeros. n.3 matrizes Índice Bem como um vetor de índice em qualquer posição subscrito. [2]. [3]. 1 5 9 13 17 [2] 2 6 10 14 18 [3]. 1 3 [2]. como desejado.. XV) No entanto. 3 1 > X [i] # Extrai os elementos [1] 9 6 3 > X [i] <.matriz (1:20. No caso de uma matriz duplamente indexados.1 > XV [iv] <. n. precisamos de uma matriz de 3 por 2 subscrito. e as linhas que contêm um NA produzir um NA no resultado. Neste caso. 2 0 10 14 18 [3]. . [2] [1]. [5] [1]. blocos) <> IV . [1]. 5.googleusercontent.com/translate_c?hl=pt-BR&ie=UTF-.1 > X <.cbind (1: n. variedades) > Xb [ib] <. N dizer. NA e valores de zero são permitidos: linhas no índice de matriz contendo um zero são ignoradas. por exemplo. 1 5 0 13 17 [2]. [5] [1]. suponha que queiramos gerar uma situação sem redução) projeto (matriz para um delineamento em blocos definidos por fatores blocks ( b níveis) e varieties ( v níveis).Uma Introdução ao R http://translate. Os índices negativos não são permitidos em matrizes índice. [2].crossprod (Xb. v) > <Ib . uma maneira mais simples direta de produzir essa matriz é a utilização de table() : 23 de 99 25/02/2011 10:36 .

os números.com/translate_c?hl=pt-BR&ie=UTF-. que tem a forma > Z <.4. Matrizes podem ser usadas em expressões aritméticas eo resultado é um conjunto formado por operações elemento por elemento do vetor de dados. A regra da reciclagem A regra precisa afetando elemento por elemento misto cálculos com vetores e matrizes é algo peculiar e difícil de encontrar nas referências.4. O dim atributos de operandos geralmente precisa ser o mesmo.1 vetores e aritmética mista matriz. A expressão é digitalizado a partir da esquerda para a direita. se A . Neste ponto. então > D <. variedades) Índice de matrizes deve ser numérica: qualquer outra forma de matriz (por exemplo. Portanto.h. Qualquer operandos vetoriais curto são estendidos através da reciclagem de seus valores 24 de 99 25/02/2011 10:36 .2) seria um sinal de erro sobre o descasamento comprimento. Da experiência que temos encontrado o seguinte para ser um guia confiável. dim(Z) representa o vetor de dimensão c(3.. dim (Z) <. B e C são matrizes semelhantes. A regra da reciclagem Precedente: matriz A () função . c (3. se o vetor h tem 24 ou menos. Seguinte: O produto externo das duas matrizes . os seus valores são reciclados a partir do início de novo para fazê-lo até o tamanho 24 (ver A regra da reciclagem ). c = dim (3. e isso se torna o vetor de dimensão do resultado. Up: matrizes e matrizes 5. Como um exemplo extremo. um caráter lógico ou matriz) fornecidos como uma matriz é tratada como um vetor de indexação. mas comuns > Z <..4.tabela (blocos.4. dim_vector) Por exemplo. Se o tamanho h é exatamente 24.4 O array() função Bem como dar uma estrutura de um vetor dim atributo.2 * A * B + C + 1 faz D uma matriz semelhante com o seu vetor de dados sendo o resultado do elementode-operações de determinado elemento. No entanto.4. se h for menor que 24. então o comando > Z <.Uma Introdução ao R http://translate.2)) usaria h criar 3 por 4 a 2 na série Z . a regra precisa quanto à matriz mista e os cálculos do vetor tem que ser considerado um pouco mais de cuidado.2) e Z[1:24] representa o vetor de dados como era no h . o resultado é o mesmo que > Z <. Anterior: Índice de matrizes . mas dim(h) <.2)) torna Z uma matriz de zeros.2) No entanto.matriz (data_vector. Up: matriz A () função 5. e Z[] com um índice vazio ou Z com não subscrito representa a matriz inteira como uma matriz.c(3.4.array (0. os vetores podem ser construídos a partir de vetores da array função.googleusercontent.c (3.matriz (h. > N <.

considere os determinantes de matrizes 2 por 2 [a. y) cos (y) / (1 + x ^ 2) > Z <. 9. Enquanto curto vetores e matrizes somente são encontradas. ylab = "Freqüência") Observe a coerção dos names atributo da tabela de freqüência para numérico. mas bonito artificial. a fim de recuperar o intervalo de valores determinantes. XLAB = "determinantes". seu produto externo é uma matriz cuja dimensão do vetor é obtido concatenando os dois vetores de dimensão (a ordem é importante). o produto externo de dois vetores normais é uma matriz duplamente subscrito (que é uma matriz de classificação. type = "h". 25 de 99 25/02/2011 10:36 . de todas as matrizes possível desta forma e representa a freqüência com que cada valor ocorre como uma trama de alta densidade.. no máximo.a% b% o Uma alternativa é > <Ab . Um exemplo: Determinantes de 2 por 2 matrizes de um dígito Como um exemplo. c. Isto equivale a encontrar a distribuição de probabilidade de o fator determinante. Observe que o operador produto externo é. . ad . respectivamente . podemos proceder da seguinte forma: > F <. d..exterior (0:09.tabela (exterior (d. O produto externo é formado pelo operador especial %o% : <Ab> . Definindo suas próprias funções R será considerado ainda em escrever suas próprias funções . as matrizes devem ter todos a mesma dim atributo ou um erro.exterior (a.function (x. Se a e b são duas matrizes numéricas. "-")) > Plot (as. O óbvio "caminho" de fazer esse problema com o for loops.. b. y.exterior (x. Qualquer vector operando mais de um operando matricial ou matriz gera um erro. Up: matrizes e matrizes 5.com/translate_c?hl=pt-BR&ie=UTF-. b. Por exemplo. 0:09) > <Fr . 1. f) Em particular.5 O produto exterior de dois vetores Uma operação importante em matrizes é o produto externo. d]. se quisermos avaliar a função f (x. que é um dígito . y) = cos (y) / (1 + x ^ 2) sobre uma grade regular de valores com x-e y-coordenadas definida pelos vetores R x e y .bc.. onde cada entrada é um inteiro não-negativo no intervalo de 0. Anterior: A função Array () . até que eles correspondam ao tamanho de qualquer outros operandos. 1). Seguinte: Generalized transposição de uma matriz . formando todos os produtos possíveis de elementos do vetor de dados a com os de b . "*") A função de multiplicação pode ser substituída por uma função arbitrária de duas variáveis. naturalmente.numeric (nomes (fr)). não-comutativa. Se as estruturas de matriz estão presentes e nenhum erro ou a coação para vetor foi precipitada.Uma Introdução ao R http://translate. se cada dígito é escolhido de forma independente e uniformemente ao acaso.. Uma boa forma de fazer isso usa o outer() função duas vezes: > D <. O problema é encontrar os determinantes. e cujos dados vetoriais tenho. o resultado é uma estrutura matricial com o mercado comum dim atributo de sua matriz operandos. fr.googleusercontent.

7 instalações Matrix Como mencionado acima. é tão ineficaz quanto a ser impraticável. A maneira mais fácil pensar desta operação é como uma generalização da transposição para as matrizes. No entanto. respectivamente. k}. . uma matriz é apenas uma matriz com dois subscritos. O resultado da função é uma matriz do mesmo tamanho que a velho.1)) é apenas a transposição de A . t(X) é a função de transpor a matriz. Por exemplo. De fato. Para este caso específico uma simples função de t() está disponível. o que for multiplicatively coerente. Por outro lado. os vetores que ocorrem em expressões de multiplicação de matrizes são automaticamente promovidos tanto aos vetores linha ou coluna.googleusercontent. ser usado como um vetor n-se no contexto como é apropriado. então > A * B é a matriz de elemento por elemento e produtos > A *%% B 26 de 99 25/02/2011 10:36 . Multiplicação equações lineares e inversão Autovalores e autovetores decomposição em valores singulares e determinantes Mínimos quadrados montagem ea decomposição QR Seguinte: equações lineares e de inversão . naturalmente. O argumento perm deve ser uma permutação dos inteiros {1. a . é um caso tão importante e específico que necessita de uma discussão em separado. perm) pode ser usado para permutar uma matriz. R contém muitos operadores e funções que estão disponíveis apenas para as matrizes. Seguinte: instalações Matrix .com/translate_c?hl=pt-BR&ie=UTF-. Um n por 1 ou por uma matriz n pode. como vemos mais tarde). Precedente: instalações Matriz ... Se.7. então B dada por > B <. A e B são matrizes quadradas do mesmo tamanho. Seguinte: Formação matrizes particionadas . para ser discutido em Loops e execução condicional . mas com dimensão dada por perm[j] se tornando o novo j ª dimensão. Up: instalações Matrix 5.. Up: matrizes e matrizes 5. Precedente: O exterior do produto de duas matrizes . por exemplo.. Precedente: Generalized transposição de uma matriz . onde k é o número de subscritos em a . uma subscrita matriz duplamente). (embora nem sempre isso é possível de forma inequívoca. Up: matrizes e matrizes 5.1 A multiplicação de matrizes O operador %*% é usado para multiplicação de matrizes.. como descrito acima.Uma Introdução ao R http://translate.aperm (A. se A é uma matriz (ou seja. então poderíamos ter usado B <.t(A) .6 transposição generalizada de uma matriz A função aperm(a. se possível. Também é surpreendente que cerca de 1 em 20 matrizes seja singular. C (2. As funções nrow(A) e ncol(A) indicar o número de linhas e colunas na matriz A .

o vetor x é a solução desse sistema de equações lineares.. que pode ser calculado por resolver (A) mas raramente é necessário. A forma quadrática x %*% A^{-1} %*% x . onde A^{-1} indica o inverso de A . Anterior: Multiplicação . Note-se que em álgebra linear. Up: instalações Matrix 5.A *% x% apenas A e b são dadas. diag(v) .googleusercontent. > Resolver (a. onde M é uma matriz.eigen (Sm) $ valores 27 de 99 25/02/2011 10:36 . então diag(k) é a k pelo k matriz identidade! Seguinte: Autovalores e autovetores . é considerado como sendo o mesmo que o primeiro. é ineficiente e potencialmente instável para calcular x <. formalmente x = A^{-1} %*% b . em seguida. O resultado desta função é uma lista de dois componentes chamados values e vectors . Em R. b) resolve o sistema. Então ev$val é o vetor de autovalores de Sm e ev$vec é a matriz de autovetores correspondentes. Se x é um vetor. Esta é a mesma convenção que o utilizado para diag() em MATLAB.7.Uma Introdução ao R http://translate. dá o principal vetor de entradas diagonais de M . um tanto confusa.x) . instalações Matrix 5. mas a operação é mais eficiente.solve(A) %*% b em vez de solve(A. Se o segundo argumento para crossprod() for omitido. O significado do diag() depende de seu argumento.3 Autovalores e autovetores A função eigen(Sm) calcula os autovalores e autovetores de uma matriz simétrica Sm .2 equações lineares e inversão Resolução de equações lineares é a inversa da multiplicação de matrizes.. que é usado em cálculos multivariada. 15 A função crossprod() formas "crossproducts". significando que crossprod(X. dá uma matriz diagonal com elementos do vetor como as entradas de diagonal.com/translate_c?hl=pt-BR&ie=UTF-. se k é um valor numérico único. Numericamente.b) . Precedente: equações lineares e inversão Up:. é o produto da matriz. >% * X% A *%% x é uma forma quadrática. y) é o mesmo que t(X) %*% y . depois de B> <. ao invés de calcular a inversa de A . Seguinte: decomposição em valores singulares e determinantes . onde v é um vetor. Se tivéssemos apenas necessário os autovalores poderíamos ter usado o serviço: evals> <. Quando.7. Além disso. retornando x (até alguma perda de precisão).eigen (Sm) atribui essa lista para ev . A atribuição > <Ev . Por outro lado diag(M) . deve ser calculado por algo como 16 x %*% solve(A.

.] R has a builtin function det to calculate a determinant. M . to give the sign and modulus (optionally on log scale). among other things. Note that a grand mean term is automatically included and need not be included explicitly as a column of X . segundo uma matriz de colunas ortonormais V .7. only. Another closely related function is qr() and its allies. D é realmente voltou como um vetor de elementos da diagonal. O resultado da svd(M) é na verdade uma lista de três componentes chamados d . cujo espaço de coluna é o espaço de linha de M e uma matriz diagonal de entradas positivas D tal que M = U %*% D %*% t(V) . Look again at the diag() function.) (see Linear models ) to lsfit() for regression modelling. determinant . including the sign. y) 28 de 99 25/02/2011 10:36 . muitas vezes com uma variedade de matrizes pode ser definida como uma função de R > <Absdet .values = TRUE) $ valores Seguinte: Mínimos quadrados montagem ea decomposição QR . you might like to consider writing a function. As a further trivial but potentially useful example.Uma Introdução ao R http://translate. evals agora detém o vetor de autovalores eo segundo componente é descartado.função (M) prod (svd (M) $ d) after which we could use absdet() as just another R function. Para grandes matrizes é melhor evitar a computação autovetores se eles não são necessários ao usar a expressão evals> <. [Hint: You will not need to use an explicit loop.lsfit(X. não é difícil perceber que > AbsdetM <. Previous: Singular value decomposition and determinants .com/translate_c?hl=pt-BR&ie=UTF-.diag() for. regression diagnostics. Up: Matrix facilities 5. to calculate the trace of a square matrix.qr(X) > b <. See the help facility for more details.prod (svd (M) $ d) calcula o valor absoluto do determinante de M . com os seus nomes. u e v . Se este cálculo fosse necessário. Se M é na praça de fato.5 Least squares fitting and the QR decomposition The function lsfit() returns a list giving results of a least squares fitting procedure. Further note that you almost always will prefer using lm(. com significados evidentes.qr.googleusercontent.7. Se a expressão > Eigen (Sm) é usado por si só como um comando os dois componentes são impressas. say tr() .coef(Xplus. então. Este consiste de uma matriz de colunas ortonormais U com o espaço mesma coluna M . and another. y) gives the results of a least squares fit where y is the vector of observations and X is the design matrix. Up: instalações Matrix 5. and also for the follow-up function ls. Precedente: Autovalores e autovetores .4 decomposição em valores singulares e determinantes A função svd(M) tem uma matriz de argumentos arbitrários. An assignment such as > ans <. Consider the following assignments > Xplus <..eigen (Sm. e calcula a decomposição em valores singulares de M .

googleusercontent. The official way to coerce an array back to a simple vector object is to use as. This is occasionally useful in its own right. Next: The concatenation function c() with arrays . > fit <. Suppose X1 and X2 have the same number of rows.Uma Introdução ao R http://translate. In the assignment > X <. Up: Arrays and matrices 5. b is essentially the result of the MATLAB `backslash' operator. The function rbind() does the corresponding operation for rows.) the arguments to cbind() must be either vectors of any length. Up: Arrays and matrices 5. The result is a matrix with the concatenated arguments arg_1 .fitted(Xplus.. that is. or row-wise..com/translate_c?hl=pt-BR&ie=UTF-. matrices can be built up from other vectors and matrices by the functions cbind() and rbind() .cbind(1. Roughly cbind() forms matrices by binding together matrices horizontally. but rather clears numeric objects of all dim and dimnames attributes. Redundancies will be discovered and removed as they are found. This alternative is the older.resid(Xplus. that is the same number of rows. Previous: Forming partitioned matrices . together with an initial column of 1 s we can use > X <.. it would now generally be replaced by the statistical models features. It is not assumed that X has full column rank. the projection onto the orthogonal complement in res and the coefficient vector for the projection in b . Next: Frequency tables from factors . X1. Hence cbind(x) and rbind(x) are possibly the simplest ways explicitly to allow the vector x to be treated as a column or row matrix respectively. . . To combine these by columns into a matrix X . Although still useful in some contexts.9 The concatenation function. the basic c() function does not. Previous: Matrix facilities . X2) The result of rbind() or cbind() always has matrix status. arg_3 . If some of the arguments to cbind() are vectors they may be shorter than the column size of any matrices present.qr. arg_2 . or matrices with the same column size. or column-wise. in which case they are cyclically extended to match the matrix column size (or the length of the longest vector if no matrices are given). arg_2 . possibly cyclically extended. y) These compute the orthogonal projection of y onto the range of X in fit .qr. and rbind() vertically.vector() 29 de 99 25/02/2011 10:36 .. as will be discussed in Statistical models in R . forming the columns. with arrays It should be noted that whereas cbind() and rbind() are concatenation functions that respect dim attributes. cbind() and rbind() As we have already seen informally.. low-level way to perform least squares calculations. are of course taken as row vectors. c() .. y) > res <.cbind( arg_1 . In this case any vector argument.8 Forming partitioned matrices.

If there are k factor arguments. Up: Top 6 Lists and data frames Listas Constructing and modifying lists Data frames Next: Constructing and modifying lists . Previous: Arrays and matrices .45] 1 1 0 1 0 0 1 0 (45. > vec <. that statef is a factor giving the state code for each entry in a data vector.75] 0 1 0 0 0 0 1 0 Extension to higher-way frequency tables is immediate. and so on.Uma Introdução ao R http://translate. for example.com/translate_c?hl=pt-BR&ie=UTF-.tapply(statef.10 Frequency tables from factors Recall that a factor defines a partition into groups. length) Further suppose that incomef is a factor giving a suitably defined “income class” for each entry in the data vector. A atribuição > statefr <. Previous: Lists and data frames .table(statef) gives in statefr a table of frequencies of each state in the sample. but more convenient than. This simple case is equivalent to. simply for this side-effect: > vec <.55] 1 1 1 1 2 0 1 3 (55. Up: Lists and data frames 30 de 99 25/02/2011 10:36 ..c(X) There are slight differences between the two.vector(X) However a similar result can be achieved by using c() with just one argument.65] 0 3 1 3 2 2 2 1 (65. Up: Arrays and matrices 5. but ultimately the choice between them is largely a matter of style (with the former being preferable). the result is a k-way array of frequencies. > statefr <.statef) statef incomef act nsw nt qld sa tas vic wa (35. Previous: The concatenation function c() with arrays . The frequencies are ordered and labelled by the levels attribute of the factor. for example with the cut() function: > factor(cut(incomes. Next: Reading data from files ..as. statef. Suppose.googleusercontent. breaks = 35+10*(0:7))) -> incomef Then to calculate a two-way table of frequencies: > table(incomef. The function table() allows frequency tables to be calculated from equal length factors. Similarly a pair of factors defines a two way cross classification.

Lst$child. no.. or. then the function length(Lst) gives the number of (top level) components it has. There is no particular need for the components to be of the same mode or type. by giving an expression of the form > name $ component_name for the same thing. a complex vector. Previous: Lists . If. whereas ' [ . Next: Data frames .googleusercontent. ]] ' is the operator used to select a single element. of course. The vector of names is in fact simply an attribute of the list like any other and may be handled as such.list(name="Fred".ages=c(4.7.com/translate_c?hl=pt-BR&ie=UTF-."name". child. The latter is a sublist of the list Lst consisting of the first entry only. The names of components may be abbreviated down to the minimum number of letters needed to identify them uniquely. when the name of the component to be extracted is stored in another variable as in > x <. is the same as Lst[[2]] and is the string "Mary" . Components of lists may also be named . a character array. If Lst is a list.9)) Components are always numbered and may always be referred to as such. and. ie. a function. is the same as Lst[[4]][1] and is the number 4 . Lst[[x]] It is very important to distinguish Lst[[1]] from Lst[1] . Other structures besides lists may. This is especially useful. Lst[[3]] and Lst[[4]] ... a list could consist of a numeric vector. and so on. these may be individually referred to as Lst[[1]] . Lst[[4]] is a vector subscripted array then Lst[[4]][1] is its first entry. the names are transferred to the sublist. This is a very useful convention as it makes it easier to get the right component if you forget the number. similarly be given a names attribute also. Up: Lists and data frames 31 de 99 25/02/2011 10:36 . Lst[[2]] . So in the simple example given above: Lst$name Lst$wife is the same as Lst[[1]] and is the string "Fred" .children=3. 6. for example. Thus Lst$coefficients may be minimally specified as Lst$coe and Lst$covariance as Lst$cov . Thus if Lst is the name of a list with four components.. a logical value. ' [[ . more conveniently. a matrix. and in this case the component may be referred to either by giving the component name as a character string in place of the number in double square brackets. further. Thus the former is the first object in the list Lst . Lst[["name"]] is the same as Lst$name .. wife="Mary". If it is a named list. Here is a simple example of how to make a list: > Lst <. one can also use the names of the list components in double square brackets.1 Lists An R list is an object consisting of an ordered collection of objects known as its components . ] ' is a general subscripting operator.ages[1] Additionally.Uma Introdução ao R http://translate. and if it is a named list the name is not included..

list. list. lists. such as dim attributes. The components used to form the list are copied when forming the new list and the originals are not affected. namely The components must be vectors (numeric. It may be displayed in matrix form.A. and character vectors are coerced to be factors. name_m = object_m ) sets up a list Lst of m components using object_1 . or logical). and matrix structures must all have the same row size .2. or other data frames. Por exemplo > Lst[5] <. the components are numbered only.ABC <. In this case all other attributes. Up: Lists and data frames 6. object_m for the components and giving them names as specified by the argument names.C) Recall that with vector objects as arguments the concatenation function similarly joined together all arguments into a single vector structure. There are restrictions on lists that may be made into data frames. whose levels are the unique values appearing in the vector.. like any subscripted object..c(list.com/translate_c?hl=pt-BR&ie=UTF-. Lists. respectively. character.2 Constructing and modifying lists New lists may be formed from existing objects by the function list() .list(matrix=Mat) Concatenating lists Previous: Constructing and modifying lists . elements. factors. logicals and factors are included as is. and data frames provide as many variables to the new data frame as they have columns. If these names are omitted. Numeric vectors.B.frame" .. numeric matrices. (which can be freely chosen).3 Data frames A data frame is a list with class "data. 6. the result is an object of mode list also. . are discarded.Uma Introdução ao R http://translate. whose components are those of the argument lists joined together in sequence..1 Concatenating lists When the concatenation function c() is given list arguments. An assignment of the form > Lst <.googleusercontent. . can be extended by specifying additional components. Matrices. A data frame may for many purposes be regarded as a matrix with columns possibly of differing modes and attributes. . Vector structures appearing as variables of the data frame must all have the same length .list( name_1 = object_1 . lists.. Previous: Constructing and modifying lists . > list. or variables. Up: Constructing and modifying lists 6. .. Making data frames attach() and detach() Working with data frames Attaching arbitrary lists Managing the search path 32 de 99 25/02/2011 10:36 . and its rows and columns extracted using matrix indexing conventions.

googleusercontent.2 attach() and detach() The $ notation. but rather masks it with another variable u in the working directory at position 1 on the search path. The attach() function takes a `database' such as a list or data frame as its argument. The attach > attach(lentils) places the data frame in the search path at position 2 . This is discussed further in Reading data from files . and what is attached is a copy of the original object. You can alter the attached values via assign . Up: Data frames 6.data. At this point an assignment such as w > u <.frame : > accountants <. v or in position 1 . Next: attach() and detach() . but the original list or data frame is unchanged.table() function to read an entire data frame from an external file. Previous: Making data frames .. Thus in the present context the variables u .Uma Introdução ao R http://translate. without the need to quote the list name explicitly each time.3. Up: Data frames 6. and provided there are no variables u . Entities at positions greater than 2 on the search path can be detached by giving their number to detach . A useful facility would be somehow to make the components of a list or data frame temporarily visible as variables under their component name. 33 de 99 25/02/2011 10:36 . for example by detach(lentils) or detach("lentils") Note: In R lists and data frames can only be attached at position 2 or above.3.frame(home=statef. lentils$w . loot=incomes.. v and w would be no longer visible.data. the simplest way is to resort once again to the $ notation: > lentils$u <. except under the list notation as lentils$u and so on. To detach a data frame. Thus suppose lentils is a data frame with three variables lentils$u . but it is much safer to always use a name. To make a permanent change to the data frame itself. lentils$v . such as accountants$statef . for list components is not always very convenient. shot=incomef) A list whose components conform to the restrictions of a data frame may be coerced into a data frame using the function as.frame() The simplest way to construct a data frame from scratch is to use the read. u . Previous: Data frames . v and w are available as variables from the data frame in their own right. this statement detaches from the search path the entity currently at position 2 .com/translate_c?hl=pt-BR&ie=UTF-. use the function > detach() More precisely.v+w does not replace the component u of the data frame.1 Making data frames Objects satisfying the restrictions placed on the columns (components) of a data frame may be used to form one using the function data.v+w However the new value of component u is not visible until the data frame is detached and attached again. Next: Working with data frames .

GlobalEnv is the workspace. Finally.GlobalEnv" "Autoloads" "package:base" where . but other classes of object as well. Up: Data frames 6. Next: Attaching arbitrary lists . finally remove all unwanted variables from the working directory and keep it as clean of left-over temporary variables as possible. y and z . In particular any object of mode "list" may be attached in the same way: attach() > attach(any. preferably. all of which have variables named x . Previous: attach() and detach() . Previous: Working with data frames .3.googleusercontent.old. add any variables you wish to keep for future reference to the data frame using the $ form of assignment. Up: Data frames 6. when working with a problem attach the appropriate data frame at position 2 . for example. we detach the data frame and confirm it has been removed from the search path.Uma Introdução ao R http://translate.. > detach("lentils") 34 de 99 25/02/2011 10:36 .list) Anything that has been attached can be detached by detach . In this way it is quite simple to work with many problems in the same directory. Initially it gives > search() [1] ".. before leaving a problem. Previous: Attaching arbitrary lists .GlobalEnv" "lentils" "Autoloads" "package:base" > ls(2) [1] "u" "v" "w" and as we see ls (or objects ) can be used to examine the contents of any position on the search path.3 Working with data frames A useful convention that allows you to work with many different problems comfortably together in the same working directory is gather together all variables for any well defined and separate problem in a data frame under a suitably informative name.3.3. and use the working directory at level 1 for operational quantities and temporary variables. Up: Data frames 6. by name. and then detach() . Next: Managing the search path .4 Attaching arbitrary lists is a generic function that allows not only directories and data frames to be attached to the search path.5 Managing the search path The function search shows the current search path and so is a very useful way to keep track of which data frames and lists (and packages) have been attached and detached. 17 After lentils is attached we have > search() [1] ". by position number or.com/translate_c?hl=pt-BR&ie=UTF-.

.0 1000 5 4. Generally this is very simple. see the R Data Import/Export manual. such as file editors or Perl 18 to fit in with the requirements of R.2 no 04 57.table() function The scan() function Accessing builtin datasets Editing data Next: The scan() function . This can be changed if necessary.00 111. Input file form with names and row labels: Price Floor Area Rooms Age Cent. Previous: Lists and data frames . By default numeric items (except row labels) are read as numeric variables and non-numeric variables. If variables are to be held mainly in data frames. If the file has one fewer item in its first line than in its second. Up: Top 7 Reading data from files Large data objects will usually be read as values from external files rather than entered during an R session at the keyboard. scan() .9 yes . So the first few lines of a file to be read as a data frame might look as follows. The function read. as we strongly suggest they should be. this arrangement is presumed to be in force. Up: Reading data from files 7. The read. that can be called directly.0 830 5 6. as factors.GlobalEnv" "Autoloads" "package:base" Next: Probability distributions ..5 no 03 57.2 no 02 54.. such as Cent.table("houses.table() can then be used to read the data frame directly > HousePrice <.75 128. > search() [1] ". Previous: Reading data from files .1 The read.heat in the example.Uma Introdução ao R http://translate. There is also a more primitive input function.8 no 05 59.50 101.0 690 6 8. There is a clear presumption by the designers of R that you will be able to modify your input files using other tools.50 131.com/translate_c?hl=pt-BR&ie=UTF-..0 900 5 1. Each additional line of the file has as its first item a row label and the values for each variable.data") Often you will want to omit including the row labels directly and use the default labels. In this 35 de 99 25/02/2011 10:36 .0 710 5 7.table() function.75 93.googleusercontent.heat 01 52. For more details on importing data into R and also exporting data. The first line of the file should have a name for each variable in the data frame. R input facilities are simple and their requirements are fairly strict and even rather inflexible.table() function To read an entire data frame directly. an entire data frame can be read directly with the read. the external file will normally have a special form.read.

dat .0)) The second argument is a dummy list structure that establishes the mode of the three vectors to be read. x <..2 The scan() function Suppose the data vectors are of equal length and are to be read in parallel.0 900 5 1. Previous: The read.table() function . header=TRUE) where the header=TRUE option specifies that the first line is a line of headings.Uma Introdução ao R http://translate.0 710 5 7.. The result. ncol=5. Input file form without row labels: Price 52.0 690 6 8.0 830 5 6. 0). and hence. Further suppose that there are three vectors.50 59.data".scan("input. The first step is to use scan() to read in the three vectors as a list. y <.2 no 128. For example > inp <. y=0)) If you wish to access the variables separately they may either be re-assigned to variables in the working frame: > label <.com/translate_c?hl=pt-BR&ie=UTF-. held in inp . The scan() function Next: Accessing builtin datasets .. the first of mode character and the remaining two of mode numeric.heat 111.8 no 93. y <.75 57. a single vector is read in.dat".9 yes The data frame may then be read as > HousePrice <. is a list whose components are the three vectors read in. the dummy list can have named components.5 no 101. in which case the names can be used to access the vectors read in. that no explicit row labels are given.inp[[1]].inp[[2]]. Floor Area Rooms Age Cent.inp$id. by implication from the form of the file. use assignments like > label <. list("".75 .inp$y or the list may be attached at position 2 of the search path (see Attaching arbitrary lists ). Up: Reading data from files 7. 36 de 99 25/02/2011 10:36 .0.googleusercontent.0 1000 5 4..matrix(scan("light.dat".00 54. If the second argument is a single value and not a list. all components of which must be of the same mode as the dummy value. case the file may omit the row label column as in the following.table("houses. byrow=TRUE) There are more elaborate input facilities available and these are detailed in the manuals. and the file is input. To separate the data items into three separate vectors.inp$x.50 57.dat". > X <. x <.read.inp[[3]] More conveniently. x=0. list(id="". as follows > inp <.scan("input.2 no 131.

O comando > xnew <. To see the list of datasets currently available use data() As from R version 2. If you want to alter the original dataset xold .. User-contributed packages can be a rich source of datasets. for example data(infert) and this can still be used with the standard packages (as in this example).3 Accessing builtin datasets Around 100 datasets are supplied with R (in package datasets ). for example data(package="rpart") data(Puromycin. In most cases this will load an R object of the same name.edit(data. 7. Use > xnew <. Previous: Reading data from files .edit(xold) will allow you to edit your data set xold . Up: Top 8 Probability distributions R as a set of statistical tables Examining the distribution of a set of data One. the simplest way is to use fix(xold) .4 Editing data When invoked on a data frame or matrix. and others are available in packages (including the recommended packages supplied with R).1 Loading data from other R packages To access data from a particular package.0. However. This is useful for making small changes once a data set has been read. which is equivalent to xold <.googleusercontent. Previous: Accessing builtin datasets . its datasets are automatically included in the search. Next: Loops and conditional execution .and two-sample tests 37 de 99 25/02/2011 10:36 . Next: Editing data . in a few cases it loads several objects.com/translate_c?hl=pt-BR&ie=UTF-. Previous: The scan() function . use the package argument. However. and on completion the changed object is assigned to xnew . package="datasets") If a package has been attached by library ..frame()) to enter new data via the spreadsheet interface.3. Up: Reading data from files 7. edit brings up a separate spreadsheet-like environment for editing.0 all the datasets supplied with R are available directly by name.Uma Introdução ao R http://translate.edit(xold) . Up: Reading data from files 7. many packages still use the earlier convention in which data was also used to load datasets into R. so see the on-line help for the object to see what to expect.

directly.. and to simulate from the distribution. ncp beta binom size.. and dmultinom and rmultinom for the multinomial distribution. In addition there are functions ptukey and qtukey for the distribution of the studentized range of samples from a normal distribution. In not quite all cases is the non-centrality parameter ncp currently available: see the on-line help for details. shape2. max uniforme weibull shape. scale Cauchy chisq df. for which it is nn )..googleusercontent. notably SuppDists . sd normal pois lambda Poisson signrank n signed rank t df. df2. Functions are provided to evaluate the cumulative distribution function P(X <= x). Distribuição R name argumentos adicionais beta shape1. ncp chi-squared exp rate exponencial f df1. The first argument is x for d xxx ..p = TRUE) or more accurate log-likelihoods (by d xxx (. scale Weibull wilcox m. The p xxx and q xxx functions all have logical arguments lower.tail = FALSE. n. scale logística negative binomial nbinom size.Uma Introdução ao R http://translate. log = TRUE) ). ' q ' for the quantile function and ' r ' for simulation ( r andom deviates).. Further distributions are available in contributed packages. .. by . ncp Student's t unif min.. the smallest x such that P(X <= x) > q). Previous: Probability distributions . p for q xxx and n for r xxx (except for rhyper . Next: Examining the distribution of a set of data . sdlog log-normal logis location. Aqui estão alguns exemplos 38 de 99 25/02/2011 10:36 . lower. log. scale gama geom prob geométrico m. k hypergeometric hyper lnorm meanlog. rsignrank and rwilcox . Up: Probability distributions 8. H(t) = log(1 .com/translate_c?hl=pt-BR&ie=UTF-. This allows. n Wilcoxon Prefix the name given here by ' d ' for the density. the probability density function and the quantile function (given q.tail and log. eg.1 R as a set of statistical tables One convenient use of R is to provide a comprehensive set of statistical tables.p and the d xxx ones have log .p xxx (t.F(t)). q for p xxx . ' p ' for the CDF.. prob binômio cauchy location. prob norm mean. ncp F gamma shape. getting the cumulative (or “integrated”) hazard function.

Uma Introdução ao R

http://translate.googleusercontent.com/translate_c?hl=pt-BR&ie=UTF-...

> ##

2-tailed p-value for t distribution
> 2*pt(-2.43, df = 13) > ## upper 1% point for an F(2, 7) distribution > qf(0.01, 2, 7, lower.tail = FALSE)

See the on-line help on RNG for how random-number generation is done in R. Next: One- and two-sample tests , Previous: R as a set of statistical tables , Up: Probability distributions 8.2 Examining the distribution of a set of data Given a (univariate) set of data we can examine its distribution in a large number of ways. The simplest is to examine the numbers. Two slightly different summaries are given by summary and fivenum and a display of the numbers by stem (a “stem and leaf” plot).
> attach(faithful) > summary(eruptions) Min. 1st Qu. Median Mean 3rd Qu. Máx. 1.600 2.163 4.000 3.488 4.454 5.100 > fivenum(eruptions) [1] 1.6000 2.1585 4.0000 4.4585 5.1000 > stem(eruptions) The decimal point is 1 digit(s) to the left of the | 16 18 20 22 24 26 28 30 32 34 36 38 40 42 44 46 48 50 | | | | | | | | | | | | | | | | | | 070355555588 000022233333335577777777888822335777888 00002223378800035778 0002335578023578 00228 23 080 7 2337 250077 0000823577 2333335582225577 0000003357788888002233555577778 03335555778800233333555577778 02222335557780000000023333357778888 0000233357700000023578 00000022335800333 0370

A stem-and-leaf plot is like a histogram, and R has a function hist to plot histograms.
> hist(eruptions) ## make the bins smaller, make a plot of density > hist(eruptions, seq(1.6, 5.2, 0.2), prob=TRUE) > lines(density(eruptions, bw=0.1)) > rug(eruptions) # show the actual data points

More elegant density plots can be made by density , and we added a line produced by density in this example. The bandwidth bw was chosen by trial-and-error as the default gives too much smoothing (it usually does for “interesting” densities). (Better automated methods of bandwidth choice are available, and in this example bw = "SJ" gives a good result.) We can plot the empirical cumulative distribution function by using the function ecdf .
> plot(ecdf(eruptions), do.points=FALSE, verticals=TRUE)

This distribution is obviously far from any standard distribution. How about the right-hand mode,

39 de 99

25/02/2011 10:36

Uma Introdução ao R

http://translate.googleusercontent.com/translate_c?hl=pt-BR&ie=UTF-...

say eruptions of longer than 3 minutes? Let us fit a normal distribution and overlay the fitted CDF.
> long <- eruptions[eruptions > 3] > plot(ecdf(long), do.points=FALSE, verticals=TRUE) > x <- seq(3, 5.4, 0.01) > lines(x, pnorm(x, mean=mean(long), sd=sqrt(var(long))), lty=3)

Quantile-quantile (QQ) plots can help us examine this more carefully.
par(pty="s") # arrange for a square figure region qqnorm(long); qqline(long)

which shows a reasonable fit but a shorter right tail than one would expect from a normal distribution. Let us compare this with some simulated data from at distribution
x <- rt(250, df = 5) qqnorm(x); qqline(x)

which will usually (if it is a random sample) show longer tails than expected for a normal. We can make a QQ plot against the generating distribution by
qqplot(qt(ppoints(250), df = 5), x, xlab = "QQ plot for t dsn") qqline(x)

Finally, we might want a more formal test of agreement with normality (or not). R provides the Shapiro-Wilk test
> shapiro.test(long) Shapiro-Wilk normality test data: long W = 0.9793, p-value = 0.01052

and the Kolmogorov-Smirnov test
> ks.test(long, "pnorm", mean = mean(long), sd = sqrt(var(long))) One-sample Kolmogorov-Smirnov test data: long D = 0.0661, p-value = 0.4284 alternative hypothesis: two.sided

(Note that the distribution theory is not valid here as we have estimated the parameters of the normal distribution from the same sample.) Previous: Examining the distribution of a set of data , Up: Probability distributions 8.3 One- and two-sample tests So far we have compared a single sample to a normal distribution. A much more common operation is to compare aspects of two samples. Note that in R, all “classical” tests including the ones used below are in package stats which is normally loaded. Consider the following sets of data on the latent heat of the fusion of ice ( cal/gm ) from Rice (1995, p.490)
Method A: 79.98 80.04 80.02 80.04 80.03 80.03 80.04 79.97 80.05 80.03 80.02 80.00 80.02 Method B: 80.02 79.94 79.98 79.97 79.97 80.03 79.95 79.97

40 de 99

25/02/2011 10:36

Uma Introdução ao R

http://translate.googleusercontent.com/translate_c?hl=pt-BR&ie=UTF-...

Boxplots provide a simple graphical comparison of the two samples.
A <- scan() 79.98 80.04 80.02 80.04 80.03 80.03 80.04 79.97 80.05 80.03 80.02 80.00 80.02 B <- scan() 80.02 79.94 79.98 79.97 79.97 80.03 79.95 79.97 boxplot(A, B)

which indicates that the first group tends to give higher results than the second. To test for the equality of the means of the two examples, we can use an unpaired t-test by
> t.test(A, B) Welch Two Sample t-test data: A and B t = 3.2499, df = 12.027, p-value = 0.00694 alternative hypothesis: true difference in means is not equal to 0 95 percent confidence interval: 0.01385526 0.07018320 sample estimates: mean of x mean of y 80.02077 79.97875

which does indicate a significant difference, assuming normality. By default the R function does not assume equality of variances in the two samples (in contrast to the similar S-PLUS t.test function). We can use the F test to test for equality in the variances, provided that the two samples are from normal populations.
> var.test(A, B) F test to compare two variances data: A and B F = 0.5837, num df = 12, denom df = 7, p-value = 0.3938 alternative hypothesis: true ratio of variances is not equal to 1 95 percent confidence interval: 0.1251097 2.1052687 sample estimates: ratio of variances 0.5837405

which shows no evidence of a significant difference, and so we can use the classical t-test that assumes equality of the variances.
> t.test(A, B, var.equal=TRUE) Two Sample t-test data: A and B t = 3.4722, df = 19, p-value = 0.002551 alternative hypothesis: true difference in means is not equal to 0 95 percent confidence interval: 0.01669058 0.06734788 sample estimates: mean of x mean of y 80.02077 79.97875

All these tests assume normality of the two samples. The two-sample Wilcoxon (or Mann-Whitney) test only assumes a common continuous distribution under the null hypothesis.
> wilcox.test(A, B)

41 de 99

25/02/2011 10:36

Up: Top 9 Grouping. p-value = 0. B) Note the warning: there are several ties in each sample. We have already seen a pair of boxplots. p-value = 0.. B) Next: Writing your own functions .points=FALSE.test(A. in which case the value of the group is the result of the last expression in the group evaluated.1 Grouped expressions R is an expression language in the sense that its only command type is a function or expression which returns a result. and so on. in particular multiple assignments are possible. xlim=range(A. Wilcoxon rank sum test with continuity correction data: A and B W = 89. Up: Loops and conditional execution 9. for example. which suggests strongly that these data are from a discrete distribution (probably due to rounding). add=TRUE) will show the two empirical CDFs. loops and conditional execution Grouped expressions Control statements Next: Control statements .googleusercontent.points=FALSE. Commands may be grouped together in braces. verticals=TRUE. do.test(A. assuming a common continuous distribution: > ks. Since such a group is also an expression it may.5962.2 Control statements 42 de 99 25/02/2011 10:36 . The Kolmogorov-Smirnov test is of the maximal vertical distance between the two ecdf's.05919 alternative hypothesis: two-sided Warning message: cannot compute correct p-values with ties in: ks.com/translate_c?hl=pt-BR&ie=UTF-. do. B) Two-sample Kolmogorov-Smirnov test data: A and B D = 0. Os seguintes > plot(ecdf(A). . and it may be used wherever any expression may be used. { expr_1 . and qqplot will perform a QQ plot of the two samples.. Previous: Grouped expressions . Up: Loops and conditional execution 9.. There are several ways to compare graphically the two samples.test(A. Previous: Probability distributions . verticals=TRUE. expr_m } . be itself included in parentheses and used a part of an even larger expression.. .Uma Introdução ao R http://translate. Previous: Loops and conditional execution . B)) > plot(ecdf(B).007497 alternative hypothesis: true location shift is not equal to 0 Warning message: Cannot compute exact p-value with ties in: wilcox. Even an assignment is an expression whose result is the value assigned.

with elements a[i] if condition[i] is true. b) and returns a vector of the length of its longest argument. 19 which will produce an array of plots corresponding to each level of the factor. Previous: Control statements . expr_1 is a vector expression. ind) > for (i in 1:length(yc)) { plot(xc[[i]]. See the help facility for further details. expr_2 is repeatedly evaluated as name ranges through the values in the vector result of expr_1 . mostly used in connection with boxplots. This is a useful function. and only evaluate their second argument if necessary.2.2 Repetitive execution: for loops. This has the form ifelse(condition.1 Conditional execution: if statements The language has available a conditional construction of the form > if ( expr_1 ) expr_2 else expr_3 where expr_1 must evaluate to a single logical value and the result of the entire expression is then evident. Up: Control statements 9. suppose ind is a vector of class indicators and we wish to produce separate plots of y versus x within classes.split(y. repeat and while There is also a for loop construction which has the form > for ( name in expr_1 ) expr_2 where name is the loop variable. ind) > yc <. Whereas & and | apply element-wise to vectors.googleusercontent. (often a sequence like 1:20 ). The “short-circuit” operators && and || are often used as part of the condition in an if statement.Uma Introdução ao R http://translate. && and || apply to vectors of length one. yc[[i]])) } (Note the function split() which produces a list of vectors obtained by splitting a larger vector according to the classes specified by a factor. otherwise b[i] . Other looping facilities include the > repeat expr 43 de 99 25/02/2011 10:36 .. the ifelse function. Code that takes a `whole object' view is likely to be both clearer and faster in R. As an example. yc[[i]]) abline(lsfit(xc[[i]]..2. now putting all plots on the one display. is as follows: > xc <.split(x. Another way to do this. Previous: Conditional execution . and expr_2 is often a grouped expression with its sub-expressions written in terms of the dummy name .) Warning : for() loops are used in R code much less often than in compiled languages. Conditional execution Repetitive execution Next: Repetitive execution . There is a vectorized version of the if / else construct.com/translate_c?hl=pt-BR&ie=UTF-. One possibility here is to use coplot() . Up: Control statements 9. a.

and learning to write useful functions is one of the main ways to make your use of R comfortable and productive.Uma Introdução ao R http://translate. Up: Top 10 Writing your own functions As we have seen informally along the way.. the R language allows the user to create objects of mode function . such as mean() . simpler ways of achieving the same end.com/translate_c?hl=pt-BR&ie=UTF-. arg_i .googleusercontent. This is an artificial example..1 Simple examples As a first example. that uses the arguments. The value of the expression is the value returned for the function. are themselves written in R and thus do not differ materially from user written functions. (usually a grouped expression). Next: Statistical models in R . Previous: Loops and conditional execution .. Control statements are most often used in connection with functions which are discussed in Writing your own functions . In the process. The function is defined as follows: 44 de 99 25/02/2011 10:36 . Previous: Writing your own functions . consider a function to calculate the two sample t-statistic..) expression The expression is an R expression.function( arg_1 . It should be emphasized that most of the functions supplied as part of the R system. since there are other.. Simple examples Defining new binary operators Named arguments and defaults The three dots argument Assignment within functions More advanced examples Âmbito Customizing the environment Object orientation Next: Defining new binary operators . arg_2 . This is the only way to terminate repeat loops. statement and the > while ( condition ) expr declaração. convenience and elegance. to calculate a value. and where more examples will emerge. . . of course. A call to the function then usually takes the form name ( expr_1 . postscript() and so on. the language gains enormously in power.) and may occur anywhere a function call is legitimate. var() . The break statement can be used to terminate any loop. possibly abnormally. expr_2 . The next statement can be used to discontinue one particular cycle and skip to the “next”. A function is defined by an assignment of the form > name <. These are true R functions that are stored in a special internal form and may be used in further expressions and so on. showing “all the steps”.. Up: Writing your own functions 10.

var(y2) s <.Uma Introdução ao R http://translate. however this is sometimes a bit tricky to use directly and it pays to have a simple function such as the following to use it safely.((n1-1)*s1 + (n2-1)*s2)/(n1+n2-2) tst <.length(y1).function(X. (This is ordinarily called the least squares estimate of the regression coefficients. namely one of the form % anything % it could have been used as a binary operator in expressions rather than in function form. %*% . yvar) e assim por diante.. y) { X <. (The backslash symbol itself is not a convenient choice as it presents special problems in this context. which returns the coefficients of the orthogonal projection of the vector y onto the column space of the matrix.twosam(data$male.bslash(Xmat.. The classical R function lsfit() does this job quite well. data$female). Thus given an by 1 vector y and an n by p matrix X then X \ y is defined as (X'X)^{-}X'y. tstat As a second example. and the outer product matrix operator %o% are other examples of binary operators defined in this way.googleusercontent. > twosam <. we may wish to make it a matrix binary operator for even more convenient use. Suppose.coef(X. y2) { n1 <. The function definition would then start as > "%!%" <. X.var(y1). for example. and more 20 . > bslash <. y) { . It in turn uses the functions qr() and qr. where (X'X)^{-} is a generalized inverse of X'X. you could perform two sample t-tests using a call such as > tstat <.function(X. Next: Named arguments and defaults . n2 <.mean(y2) s1 <.yb2)/sqrt(s*(1/n1 + 1/n2)) TST } With this function defined. we choose ! for the internal character. yb2 <. If so.) The matrix multiplication operator.qr(X) qr..(yb1 .. consider a function to emulate directly the MATLAB backslash command. y) } After this object is created it may be used in statements such as > regcoeff <.coef() in the slightly counterintuitive way above to do this part of the calculation. Previous: Simple examples . Hence there is probably some value in having just this part isolated in a simple to use function if it is going to be in frequent use.length(y2) yb1 <.2 Defining new binary operators Had we given the bslash() function a different name.) This would ordinarily be done with the qr() function. 45 de 99 25/02/2011 10:36 .) The function could then be used as X %!% y . } (Note the use of quote marks. Up: Writing your own functions 10.com/translate_c?hl=pt-BR&ie=UTF-.mean(y1).function(y1. s2 <.

data. Up: Writing your own functions 10. limit=20) > ans <. For example..function(data. or as > ans <... if fun1 were defined as > fun1 <.) 46 de 99 25/02/2011 10:36 . for more details on the par() function. graph=TRUE. data.) { [omitted statements] if (graph) par(pch="*". graph=TRUE.. Next: The three dots argument . they may be given in any order.3 Named arguments and defaults As first noted in Generating regular sequences . if arguments to called functions are given in the “ name = object ” form.frame. TRUE.. of the function.) This can be done by including an extra argument.. An outline example is given below. It is important to note that defaults may be arbitrary expressions... they are not restricted to be constants as in our simple example here. df) which is now equivalent to the three cases above. Previous: Named arguments and defaults . df. graph=TRUE. . graph=TRUE. literally ' .com/translate_c?hl=pt-BR&ie=UTF-.function(data.frame. Furthermore the argument sequence may begin in the unnamed.fun1(d.Uma Introdução ao R http://translate.frame=df) are all equivalent. } it could be called as > ans <. df. limit=20) { . fun1 <. and specify named arguments after the positional arguments. ' argumento Another frequent requirement is to allow one function to pass on argument settings to another. in which case they may be omitted altogether from the call when the defaults are appropriate. '. data. 20) > ans <. Next: Assignment within functions . Previous: Defining new binary operators ..function(data. limit=20. .. For example many graphics functions use the function par() and functions like plot() allow the user to pass on graphical parameters to par() to control the graphical output.fun1(d. limit=10) which changes one of the defaults.fun1(data=d.fun1(d. positional form.frame.googleusercontent. Up: Writing your own functions 10. df. which may then be passed on. limit=20.fun1(d. limit) { [function body omitted] } then the function may be invoked in several ways.. graph. Thus if there is a function fun1 defined by > fun1 <. (See The par() function . In many cases arguments can be given commonly appropriate default values. for example > ans <.. data. even involving other arguments to the same function.4 The ' .

and N is the b by v incidence matrix.as. respectively. varieties) { blocks <. [more omissions] } Next: More advanced examples . This is a somewhat advanced.as..) A block design is defined by two factors. varieties) A <.vector(table(blocks)) # remove dim attr R <.table(blocks. then either the “superassignment” operator.length(levels(varieties)) K <. though hardly difficult.vector(table(varieties)) # remove dim attr N <.com/translate_c?hl=pt-BR&ie=UTF-. These are discussed further in Scope . Previous: More advanced examples . blockcv=sv$u.has different semantics in R.1/sqrt(K) * N * rep(1/sqrt(R). topic and is not covered further here. Up: More advanced examples 10.length(levels(blocks)) varieties <. where A = K^{-1/2}NR^{-1/2}. v)) sv <. Up: Writing your own functions 10.or the function assign() can be used.factor(varieties) # minor safety move v <. rep(b. if a little pedestrian. S-PLUS users should be aware that <<. then the efficiency factors are defined as the eigenvalues of the matrix E = I_v .6 More advanced examples Efficiency factors in block designs Dropping all names in a printed array Recursive numerical integration Next: Dropping all names in a printed array . If R and K are the v by v and b by b replications and block size matrices. example of a function. See the help document for details.. One way to write the function is given below. consider finding the efficiency factors for a block design. <<.googleusercontent.R^{-1/2}N'K^{-1}NR^{-1/2} = I_v . Previous: Assignment within functions . If global and permanent assignments are intended within a function. Previous: The three dots argument .1 Efficiency factors in block designs As a more complete.function(blocks. Next: Scope .sv$d^2. Up: Writing your own functions 10. say blocks ( b levels) and varieties ( v levels).5 Assignments within functions Note that any ordinary assignments done within the function are local and temporary and are lost after exit from the function .qr(X) does not affect the value of the argument in the calling program.Uma Introdução ao R http://translate.factor(blocks) # minor safety move b <. Thus the assignment X <.as. varietycv=sv$v) } 47 de 99 25/02/2011 10:36 . (Some aspects of this problem have already been discussed in Index matrices .6. > bdeff <.svd(A) list(eff=1 .as. To understand completely the rules governing the scope of R assignments the reader needs to be familiar with the notion of an evaluation frame .A'A.

no. If the one-panel trapezium rule answer is close enough to the two panel. nrow(X)).Uma Introdução ao R http://translate.dimnames() .. shown below.3 Recursive numerical integration Functions may be recursive. but also the block and variety canonical contrasts. Removing the dimnames attribute will not achieve this effect. rm(temp) This can be much more conveniently done using a function. The result of the function is a list giving not only the efficiency factors as the first component. but rather the array must be given a dimnames attribute consisting of empty strings. or indeed variables. There is. i) } dimnames(a) <.dimnames <. Up: More advanced examples 10.list() l <. X > temp <.0 for(i in dim(a)) { d[[l <. an array may be printed in close format using > no. 48 de 99 25/02/2011 10:36 .function(a) { ## Remove all dimension names from an d <.6. Next: Recursive numerical integration .l + 1]] <.googleusercontent. Note.d um } array for compact printing. Previous: Dropping all names in a printed array . it is often useful to print them in close block form without the array names or numbers. The integrand is evaluated at the end points of the range and in the middle. are not inherited by called functions in higher evaluation frames as they would be if they were on the search path. a heavy overhead. For example to print a matrix. no. however.6. then the latter is returned as the value. The result is an adaptive integration process that concentrates function evaluations in regions where the integrand is farthest from linear.rep("".. that such functions. and the function is only competitive with other algorithms when the integrand is both smooth and very difficult to evaluate. The example below shows a naive way of performing one-dimensional numerical integration. however. since sometimes these give additional useful qualitative information. Otherwise the same process is recursively applied to each panel. Previous: Efficiency factors in block designs . ncol(X))) > temp.2 Dropping all names in a printed array For printing purposes with large matrices or arrays.com/translate_c?hl=pt-BR&ie=UTF-.dimnames(X) This is particularly useful for large integer arrays. Up: More advanced examples 10. It also illustrates how some effective and useful user functions can be quite short.X > dimnames(temp) <. rep("".list(rep("". and may themselves define functions within themselves. With this function defined. where patterns are the real interest rather than the values. It is numerically slightly better to work with the singular value decomposition on this occasion rather than the eigenvalue routines. as a “wrap around” to achieve the same result.

a.f(b) a0 <. First we define a function called cube .1. Consider the following function definition. fd.(a + b)/2 h <. d. a. eps.a2) < eps || lim == 0) return(a1 + a2) else { return(fun(f. Therefore it is a free variable and the scoping rules must be used to ascertain the value that is to be associated with it. it details one of the major differences between S-PLUS and R. fun)) } } fa <. a1. a0. cube <. This is called lexical scope . x is a formal parameter.function(f.function(n) { sq <. fa.. However.function(x) { y <. a2. Under static scope ( S-PLUS ) the value is that associated with a global variable named n . The example is also given partly as a little puzzle in R programming. The symbols which occur in the body of a function can be divided into three classes. area <. eps. Local variables are those whose values are determined by the evaluation of expressions in the body of the functions. fb.function() n*n n*sq() } The variable n in the function sq is not an argument to that function. eps = 1. fun) { ## function `fun1' is only visible inside `area' d <. lim .function(f. fd.a))/2 fun1(f. b.f(d) a1 <.googleusercontent. b. lim. formal parameters. fun) + fun(f. Their values are determined by the process of binding the actual function arguments to the formal parameters.a1 .2*x print(x) print(y) print(z) } In this function.((fa + fb) * (b . In R the free variable bindings are resolved by first looking in the environment in which the function was created.f(a) fb <. lim . Under 49 de 99 25/02/2011 10:36 . eps. fa.h * (fa + fd) a2 <. The formal parameters of a function are those occurring in the argument list of the function. d.(b . Up: Writing your own functions 10. Variables which are not formal parameters or local variables are called free variables. b. fun1) } Âmbito Object orientation Next: Customizing the environment .7 Scope The discussion in this section is somewhat more technical than in other parts of this document. fa. lim = 10) { fun1 <.Uma Introdução ao R http://translate.1. eps. a0. f <. fb. lim. Free variables become local variables if they are assigned to.0e-06.h * (fd + fb) if(abs(a0 . local variables and free variables.a)/4 fd <.. Previous: More advanced examples .com/translate_c?hl=pt-BR&ie=UTF-. a. a. fb. b. y is a local variable and z is a free variable.

"\n\n") } withdraw = function(amount) { if(amount > total) stop("You don't have that much money!\n") total <<. a function for making deposits and a function for stating the current balance.total + amount cat(amount. "withdrawn. lexical scope (R) it is the parameter to the function cube since that is the active binding for the variable n at the time the function sq was defined.has been used in a function that was returned as the value of another function will the special behavior described here occur.googleusercontent. A functioning bank account needs to have a balance or total.. Because these functions are defined in an environment which contains total . "\n\n") } ) } ross <. a function for making withdrawals. is used to change the value associated with total . <<. In the following example we show how R can be used to mimic a bank account.account <. This operator looks back in enclosing environments for an environment that contains the symbol total and when it finds such an environment it replaces the value.total . total. We achieve this by creating the three functions within account and then returning a list containing them. total.com/translate_c?hl=pt-BR&ie=UTF-. The special assignment operator.creates a global variable and assigns the value of the right hand side to it 21 . Your balance is".. ## first evaluation in S S> cube(2) Error in sq(): Object "n" not found Largaram S> n <. with the value of right hand side. Only when <<.open.Uma Introdução ao R http://translate.amount cat(amount.account(100) robert <. in that environment. they will have access to its value.. Your balance is". If the global or top-level environment is reached without finding the symbol total then that variable is created and assigned to there.account(200) ross$withdraw(30) ross$balance() robert$balance() ross$deposit(50) ross$balance() ross$withdraw(500) 50 de 99 25/02/2011 10:36 . total. For most users <<.3 S> cube(2) [1] 18 ## then the same function evaluated in R R> cube(2) [1] 8 Lexical scope can also be used to give functions mutable state . "deposited.open. When account is invoked it takes a numerical argument total and returns a list containing the three functions. The difference between evaluation in R and evaluation in S-PLUS is that S-PLUS looks for a global variable called n while R first looks for a variable called n in the environment created when cube was invoked. "\n\n") } balance = function() { cat("Your balance is".function(total) { list( deposit = function(amount) { if(amount <= 0) stop("Deposits must be positive!\n") total <<. open.

Among the other generic functions are plot() 51 de 99 25/02/2011 10:36 . If that variable is unset. There is a site initialization file and every directory can have its own special initialization file. Finally. Up: Writing your own functions 10."\nAdios\n")) # Is it } time for lunch? Previous: Customizing the environment .First and . the special functions .getenv("HOME"). > . Up: Writing your own functions 10. If the argument lacks any class attribute. is (normally) executed at the very end of the session.Rprofile file is found in the startup directory.Rprofile 22 can be placed in any directory. the definition in the example below alters the prompt to $ and sets up various other useful things that can then be taken for granted in the rest of the session. Thus. length=999) # custom numbers and printout x11() # for graphics par(pch = "+") # plotting character source(file..site in the R home subdirectory etc is used.First <. the file Rprofile. .Rprofile files. then R looks for a . a generic function performs a task or action on its arguments specific to the class of the argument itself .off() # a small safety measure. there is always a default action provided. Previous: Scope .First() in either of the two profile files or in the . A definition in later files will mask definitions in earlier files.8 Customizing the environment Users can customize their environment in several different ways. the file it points to is used instead of the . This file gives individual users control over their workspace and allows for different startup procedures in different working directories. continue="+\t") # $ is the prompt options(digits=5. If no . "R". For example.com/translate_c?hl=pt-BR&ie=UTF-. personal. The class mechanism offers the user the facility of designing and writing generic functions for special purposes.googleusercontent. > ..RData image has a special status.function() { graphics. if defined.First() . Next: Object orientation . or has a class not catered for specifically by the generic function in question. generic functions and object orientation The class of an object determines how it will be treated by what are known as generic functions. An example is given below.Uma Introdução ao R http://translate. This file should contain the commands that you want to execute every time R is started under your system. Rprofile. profile file named . An example makes things clearer.Last() .Last can be used.site . the user profile. It is automatically performed at the beginning of an R session and may be used to initialize the environment. "mystuff.function() { options(prompt="$ ". the sequence in which files are executed is.path(Sys. Any function named . cat(paste(date(). Put the other way round.Rprofile file in the user's home directory and uses that (if it exists).9 Classes. The location of the site initialization file is taken from the value of the R_PROFILE environment variable. A second. If R is invoked in that directory then that file will be sourced.Last <. If the environment variable R_PROFILE_USER is set.RData and then .R")) # my personal functions library(MASS) # attach a package } Similarly a function .

.aov* coef. for example > coef function (object.na(z)] } The reader is referred to the R Language Definition for a more complete discussion of this mechanism. Up: Top 52 de 99 25/02/2011 10:36 .frame" include [ [[<...listof* [5] coef. For example the plot() function has a default method and variants for objects of classes "data..aov") A single object matching 'coef. "factor" . for displaying objects graphically.summary.frame" . To see what methods are available we can use methods() > methods(coef) [1] coef.googleusercontent. Previous: Writing your own functions .mean plot summary A currently complete list can be got by using the methods() function: > methods(class="data.any as. For example. the functions that can accommodate in some fashion objects of class "data. .frame") Conversely the number of classes a generic function can handle can also be quite large.. We can read these by either of > getAnywhere("coef.com/translate_c?hl=pt-BR&ie=UTF-.Uma Introdução ao R http://translate.object$coef z[!is.Arima* coef.na(z)] } > getS3method("coef". .nls* coef.. and more.default* coef.aov' was found It was found in the following places registered S3 method for coef from namespace stats namespace:stats com valor function (object. "aov") function (object. Next: Graphics . "density" . A complete list can be got again by using the methods() function: > methods(plot) For many generic functions the function body is quite short. .object$coef z[!is.) UseMethod("coef") The presence of UseMethod indicates this is a generic function.matrix [<... summary() for summarizing analyses of various types.) { z <. The number of generic functions that can treat a class in a specific way can be quite large.nls* Non-visible functions are asterisked In this example there are six methods. and anova() for comparing statistical models. none of which can be seen by typing its name.) { z <.

the determining variables.. 53 de 99 25/02/2011 10:36 . Later we make some rather more ambitious presumptions. i = 1. 11 Statistical models in R This section presumes the reader has some familiarity with statistical methodology. and the second an explicit one.. . . Suppose y .. n. without an intercept term). Formulae for statistical models Linear models Generic functions for extracting model information Analysis of variance and model comparison Updating fitted models Generalized linear models Nonlinear least squares and maximum likelihood models Some non-standard models Next: Linear models . Previous: Statistical models in R .Uma Introdução ao R http://translate. In matrix terms this would be written y = X beta + e where the y is the response vector. Up: Statistical models in R 11. x_p. x1 . C .. Exemplos Before giving a formal specification. y ~ x y ~ 1 + x Both imply the same simple linear regression model of y on x. a few examples may usefully set the picture. sigma^2).googleusercontent. . homoscedastic errors y_i = sum_{j=0}^p beta_j x_{ij} + e_i. are factors..1 Defining statistical models. The following formulae on the left side below specify statistical models as described on the right. X is a matrix and A .. x0 .com/translate_c?hl=pt-BR&ie=UTF-. where the e_i are NID(0. . y ~ 0 + x y ~ -1 + x y ~ x . x2 . The requirements for fitting statistical models are sufficiently well defined to make it possible to construct general tools that apply in a broad spectrum of problems. in particular with regression analysis and the analysis of variance. x . . the basic output is minimal. are numeric variables..1 Simple linear regression of y on x through the origin (that is. and one needs to ask for the details by calling extractor functions... formulae The template for a statistical model is a linear regression model with independent.. B . As we mention in the introduction. namely that something is known about generalized linear models and nonlinear regression. x_1. X is the model matrix or design matrix and has columns x_0. The first has an implicit intercept term. Very often x_0 will be a column of ones defining an intercept term. . R provides an interlocking suite of facilities that make fitting statistical models very simple.

and the second uses explicit powers. determined by factor C. as basis. The last form produces explicit estimates of as many different intercepts and slopes as there are levels in A.2) y ~ 1 + x + I(x^2) Polynomial regression of y on x of degree 2. y ~ A Single classification analysis of variance model of y. A and B.. log(y) ~ x1 + x2 Multiple regression of the transformed variable. y ~ A * x y ~ A/x y ~ A/(1 + x) .. The first form uses orthogonal polynomials. Both formulae specify the same model. on x1 and x2 (with an implicit intercept term). The first two specify the same crossed classification and the second two specify the same nested classification. is response ~ op_1 term_1 op_2 term_2 op_3 term_3 . y y y y ~ ~ ~ ~ A*B A + B + A:B B %in% A A/B Two factor non-additive model of y on A and B. The form. vectors or matrices connected by formula operators . with classes determined by A. (or expression evaluating to a vector or matrix) defining the response variable(s).1 Separate simple linear regression models of y on x within the levels of A. y ~ (A + B + C)^2 y ~ A*B*C . term_i is either a vector or matrix expression. The operator ~ is used to define a model formula in R. onde resposta is a vector or matrix. either + or . or a formula expression consisting of factors. a factor. and with covariate x. For example a split plot experiment. and error strata determined by factor C. op_i is an operator. y ~ X + poly(x.. (the first is optional). y ~ A*B + Error(C) An experiment with two treatment factors. for an ordinary linear model..A:B:C Three factor experiment but with a model containing main effects and two factor interactions only. log(y). with whole plots (and hence also subplots). y ~ poly(x. implying the inclusion or exclusion of a term in the model.com/translate_c?hl=pt-BR&ie=UTF-. with classes determined by A.2) Multiple regression y with model matrix consisting of the matrix X as well as polynomial terms in x to degree 2. y ~ A + x Single classification analysis of covariance model of y.. or 1 . In abstract terms all four specify the same model subspace. 54 de 99 25/02/2011 10:36 . with different codings.Uma Introdução ao R http://translate.googleusercontent.

com/translate_c?hl=pt-BR&ie=UTF-. if the intercept is 55 de 99 25/02/2011 10:36 . M^n All terms in M together with “interactions” up to order n I( M ) Insulate M . This is not the case in other contexts. as each provides one column of the model matrix (and the intercept will provide a column of ones if included in the model). Contrasts Previous: Formulae for statistical models .. The formula operators are similar in effect to the Wilkinson and Rogers notation used by such programs as Glim and Genstat.. . Note that inside the parentheses that usually enclose function arguments all operators have their normal arithmetic meaning. 1992. but with a different coding. omitting the constant term. Note particularly that the model formulae specify the columns of the model matrix . the specification of the parameters being implicit. One inevitable change is that the operator ' . This is easy if we have continuous variables. for example in specifying nonlinear models. M_1 %in% M_2 Similar to M_1 : M_2 .. The function I() is an identity function used to allow terms in model formulae to be defined using arithmetic operators. First. M_1 / M_2 M_1 + M_2 %in% M_1 . p. . then the “subclasses” factor. . The notation is summarized below (based on Chambers & Hastie.) For ordered factors the k . A 1 stands for an intercept column and is by default included in the model matrix unless explicitly removed.. and that term appears in the model matrix. k. M_1 : M_2 The tensor product of M_1 and M_2 .. kth levels of the factor. Inside M all operators have their normal arithmetic meaning. M_1 . What about a k-level factor A ? The answer differs for unordered and ordered factors. If both terms are factors.29): Y~M Y is modeled as M .1.Uma Introdução ao R http://translate. ' becomes ' : ' since the period is a valid name character in R. For unordered factors k ..1 columns are the orthogonal polynomials on 1. it is not the whole story.1 columns are generated for the indicators of the second. (Thus the implicit parameterization is to contrast the response at each level with that at the first. In all cases each term defines a collection of columns either to be added to or removed from the model matrix.M_2 Include M_1 leaving out terms of M_2 . . M_1 * M_2 M_1 + M_2 + M_1 : M_2 .1 Contrasts We need at least some idea how the model formulae specify the columns of the model matrix.googleusercontent. Although the answer is already complicated. M_1 + M_2 Include M_1 and M_2 . Up: Formulae for statistical models 11.

as the contrast scheme to be used can be set for each term in the model using the functions contrasts and C . model formulae in R will normally generate the models that an expert statistician would expect. "contr. The important (but technically optional) parameter data = production specifies that any variables needed to construct the model should come first from the production data frame . Up: Statistical models in R 11. We have still not finished. Up: Statistical models in R 11. Previous: Linear models . Previous: Formulae for statistical models .3 Generic functions for extracting model information The value of lm() is a fitted model object.frame ) Por exemplo > fm2 <. Estes incluem add1 deviance formula predict step alias drop1 kappa print summary anova effects labels proj vcov coef family plot residuals 56 de 99 25/02/2011 10:36 . provided that marginality is preserved. the whole behavior can be changed by the options setting for contrasts . Next: Generic functions for extracting model information . plotted and so on by using generic functions that orient themselves to objects of class "lm" . a model with an interaction but not the corresponding main effects will in general lead to surprising results. and is for experts only. We have not yet considered interaction terms: these generate the products of the columns introduced for their component terms. Second. "contr. data = data. data = production) would fit a multiple regression model of y on x1 and x2 (with implicit intercept term).poly")) The main reason for mentioning this is that R and S have different defaults for unordered factors. and a streamlined version of the call is as follows: > fitted.lm( formula . the first such term is encoded into k columns giving the indicators for all the levels. This is the case regardless of whether data frame production has been attached on the search path or not . So if you need to compare your results to those of a textbook or paper which used S-PLUS . Next: Analysis of variance and model comparison . omitted in a model that contains a factor term.model <. Fitting. as treatment contrasts (R's default) are thought easier for newcomers to interpret. Information about the fitted model can then be displayed.lm(y ~ x1 + x2.poly")) This is a deliberate difference.treatment".googleusercontent. you will need to set options(contrasts = c("contr. S using Helmert contrasts. extracted.com/translate_c?hl=pt-BR&ie=UTF-.helmert".Uma Introdução ao R http://translate. Although the details are complicated.. for example.2 Linear models The basic function for fitting ordinary multiple models is lm() .. technically a list of results of class "lm" . The default setting in R is options(contrasts = c("contr.

googleusercontent. formula( object ) Extract the model formula. Most often used implicitly. Short form: resid( object ) .. 57 de 99 25/02/2011 10:36 . anova( object_1 . The model with the smallest value of AIC (Akaike's An Information Criterion) discovered in the stepwise search is returned. plot( object ) Produce four plots.com/translate_c?hl=pt-BR&ie=UTF-. The value is a vector or matrix of predicted values corresponding to the determining variable values in data. residuals( object ) Extract the (matrix of) residuals. Long form: coefficients( object ) . newdata= data.frame ) The data frame supplied must have variables specified with the same labels as the original. summary( object ) Print a comprehensive summary of the results of the regression analysis.frame . showing residuals. fitted values and some diagnostics.. deviance( object ) Residual sum of squares. print( object ) Print a concise version of the object. weighted as appropriate. predict( object . object_2 ) Compare a submodel with an outer model and produce an analysis of variance table. weighted if appropriate.Uma Introdução ao R http://translate. A brief description of the most commonly used ones is given below. coef( object ) Extract the regression coefficient (matrix). step( object ) Select a suitable model by adding or dropping terms and preserving hierarchies.

“within farms. This does not give different information to the default. and most of the generic functions listed in the table in Generic functions for extracting model information apply.com/translate_c?hl=pt-BR&ie=UTF-.formula .1 ANOVA tables Note also that the analysis of variance table (or tables) are for a sequence of fitted models. A more flexible alternative to the default full ANOVA table is to compare two or more models directly using the anova() function. namely between and within the levels of the factor. The model formula response ~ mean. fitted. when it defines a two strata experiment. Up: Analysis of variance and model comparison 11.formula is simply a factor.aov(yield ~ v + n*p*k + Error(farms/blocks). data= data.4. vcov( object ) Returns the variance-covariance matrix of the main parameters of a fitted model object. ..formula + Error( strata.1 .Uma Introdução ao R http://translate. For multistratum experiments the procedure is first to project the response onto the error strata. The fitted models being compared would usually be an hierarchical sequence.googleusercontent. data=farm.model. 58 de 99 25/02/2011 10:36 .4 Analysis of variance and model comparison The model fitting function aov(formula. of course. strata. For further details. or balanced incomplete block designs with recovery of inter-block information.. but rather makes it easier to comprehend and control. It should be noted that in addition aov() allows an analysis of models with multiple error strata such as split plot experiments. Previous: Generic functions for extracting model information . The sums of squares shown are the decrease in the residual sums of squares resulting from an inclusion of that term in the model at that place in the sequence.model. again in sequence. namely “between farms”.. a model formula such as that in: > fm <. Next: Updating fitted models .data) would typically be used to describe an experiment with mean model v + n*p*k and three error strata..2 . > anova( fitted. ANOVA tables Previous: Analysis of variance and model comparison . For example. with all determining variables factors. see Chambers & Hastie (1992). Up: Statistical models in R 11. and to fit the mean model to each projection. In the simplest case.) The display is then an ANOVA table showing the differences between the fitted models when fitted in sequence.frame ) operates at the simplest level in a very similar way to the function lm() . Hence only for orthogonal experiments will the order of inclusion be inconsequential. between blocks” and “within blocks”.formula ) specifies a multi-stratum experiment with error strata defined by the strata.

y.googleusercontent. Note especially that if the data= argument is specified on the original call to the model fitting function.) ~ . Por exemplo > fmfull <.update(fm05. Up: Statistical models in R 11. and is usually written eta = beta_1 x_1 + beta_2 x_2 + . of interest and stimulus variables x_1.Uma Introdução ao R http://translate. whose values influence the distribution of the response.lm(y ~ x1 + x2 + x3 + x4 + x5. new.. + beta_p x_p. This linear function is called the linear predictor . Other functions for exploring incremental sequences of models are add1() . The stimulus variables influence the distribution of y through a single linear function. The names of these give a good clue to their purpose. x_2. but with slightly different meaning. drop1() and step() .) would fit a five variate multiple regression with variables (presumably) from the data frame production ... sqrt(. only. mu. can be used to stand for “the corresponding part of the old model formula”. and fit a variant on the model where the response had a square root transform applied. . phi)) 59 de 99 25/02/2011 10:36 . fit an additional model including a sixth regressor variable. hence x_i has no influence on the distribution of y if and only if beta_i is zero.com/translate_c?hl=pt-BR&ie=UTF-. ' can also be used in other contexts.model <. '. Previous: Updating fitted models .5 Updating fitted models The update() function is largely a convenience function that allows a model to be fitted that differs from one previously fitted usually by just a few additional or removed terms..update( old.lm(y ~ . > fm05 <.. Up: Statistical models in R 11. phi) = exp((A/phi) * (y lambda(mu) . Previous: Analysis of variance and model comparison . Its form is > new. . . Next: Generalized linear models .6 Generalized linear models Generalized linear modeling is a development of linear models to accommodate both non-normal response distributions and transformations to linearity in a clean and straightforward way. .gamma(lambda(mu))) + tau(y. only . this information is passed on through the fitted model object to update() and its allies. The distribution of y is of the form f_Y(y. data = production) > fm6 <.formula ) In the new. + x6) > smf6 <.. ' .model . but for full details see the on-line help. The name ' .formula the special name consisting of a period. Por exemplo.update(fm6. A generalized linear model may be described in terms of the following sequence of assumptions: There is a response. Next: Nonlinear least squares and maximum likelihood models . data = production) would fit a model with response y and regressor variables all other variables in the data frame production . ~ .

inverse identity .. identity . but in other cases this function is implied by the response distribution. where phi is a scale parameter (possibly known).. 1/mu^2 .googleusercontent. log 1/mu^2 .2 The glm() function Since the distribution of the response depends on the stimulus variables through a single linear function only . ell().gaussian poisson quasi Link functions logit . inverse . The reader is referred to any of the current reference works on the subject for full details.1 Families The class of generalized linear models handled by facilities supplied in R includes gaussian . inverse . Previous: Families . log .com/translate_c?hl=pt-BR&ie=UTF-. a link function and various other pieces of information that are needed to carry out the modeling exercise is called the family of the generalized linear model. and is constant for all observations. Up: Generalized linear models 11. eta = m^{-1}(mu) = ell(mu) and this inverse function. In the latter case the variance function must be specified as a function of the mean. Those automatically available are shown in the following table: Nome de Família binomial gaussian Gamma inverse. The R function to fit a generalized linear model is glm() which uses the form 60 de 99 25/02/2011 10:36 . at least approximately. Previous: Generalized linear models . log . assumed known but possibly varying with the observations. probit . binomial . identity . poisson .6. the same mechanism as was used for linear models can still be used to specify the linear part of a generalized model. These assumptions are loose enough to encompass a wide class of models useful in statistical practice. cloglog . mu.Uma Introdução ao R http://translate. but tight enough to allow the development of a unified methodology of estimation and inference. cloglog identity . is called the link function . Up: Generalized linear models 11. sqrt The combination of a response distribution. such as McCullagh & Nelder (1989) or Dobson (1990). Each response distribution admits a variety of link functions to connect the mean with the linear predictor. log . inverse . sqrt logit . log . is a smooth invertible function of the linear predictor: mu = m(eta). The mean. probit . and $\mu$ is the mean of y. So it is assumed that the distribution of y is determined by its mean and possibly a scale parameter as well. inverse gaussian and gamma response distributions and also quasi-likelihood models where the response distribution is not explicitly specified. A represents a prior weight. log identity . The family has to be specified in a different way.6. Famílias The glm() function Next: The glm() function .

F(z) = e^z/(1+e^z). In the case of the quasi family. that is the age at which the chance of blindness for a male inhabitant is 50%. its use is quite simple. The data is shown below: Idade: 20 35 45 55 70 No. Note how the gaussian family is not automatically provided with a choice of links. n = rep(50. so no parameter is allowed.5). data=sales) but much less efficiently. data = sales) achieves the same result as > fm <.com/translate_c?hl=pt-BR&ie=UTF-. If a problem requires a gaussian family with a nonstandard link. both models have the form y ~ B(n.70).data.glm(y ~ x1 + x2.glm( formula . the point at which the argument of the distribution function is zero. Where there is a choice of links.55. which is the instrument by which the family is described. artificial example. blind: 6 17 26 37 44 The problem we consider is to fit both logistic and probit models to this data.17. supplied family generators are given under “Family Name” in the table in Families . y = c(6.. data= data. > fitted.lm(y ~ x1+x2. and in the logit case (the default). The gaussian family A call such as > fm <. In both cases the LD50 is LD50 = . The binomial family Consider a small. as we shall see later. The first step is to set the data up as a data frame > kalythos <. F(z) = Phi(z) is the standard normal distribution function. tested: 50 50 50 50 50 No. Some examples make the process clear.26.googleusercontent. from Silvey (1970).model <. this can usually be achieved through the quasi family.35. the name of the link may also be supplied with the family name. the variance function may also be specified in this way. the effects of which become more marked with increasing age.frame(x = c(20. The names of the standard. If y is the number of blind at age x and n the number tested.frame ) The only new feature is the family. On the Aegean island of Kalythos the male inhabitants suffer from a congenital eye disease. in parentheses as a parameter.. Samples of islander males of various ages were tested for blindness and the results recorded. family= family. F(beta_0 + beta_1 x)) where for the probit case.beta_0/beta_1 that is.Uma Introdução ao R http://translate.generator .generator .44)) To fit a binomial model using glm() there are three possibilities for the response: 61 de 99 25/02/2011 10:36 .37. Although this may seem a little complicated at first sight. and to estimate for each model the LD50.45. family = gaussian. It is the name of a function that generates a list of functions and expressions that together define and control the model and estimation process.

and so must be a 0/1 vector. this family provides a way of fitting gaussian models with non-standard link functions or variance functions. beta_1 = 1/theta_1. whose actual distribution is often multinomial. and beta_2 = theta_2/theta_1. Since quasi-likelihood estimation uses formally identical techniques to those for the gaussian distribution. c(ldp.601 years respectively. To see the results of each fit we could use > summary(fmp) > summary(fml) Both models fit (all too) well. Here we need the second of these conventions.Uma Introdução ao R http://translate. but rather only a link function and the form of the variance function as it depends on the mean.theta_2) + e which may be written alternatively as y = 1 / (beta_1 x_1 + beta_2 x_2) + e where x_1 = z_2/z_1. For quasi-likelihood estimation and inference the precise response distribution is not specified.glm(Ymat ~ x. family = poisson(link=sqrt). data = worm.com/translate_c?hl=pt-BR&ie=UTF-. It even forms a major part of the use of non-gaussian generalized models overall. Poisson models With the Poisson family the default link is the log . ldl) The actual estimates from this data are 43. family = binomial(link=probit). kalythos$n . If the response is a two-column matrix it is assumed that the first column holds the number of successes for the trial and the second holds the number of failures.663 years and 43.googleusercontent..glm(Ymat ~ x. for example for the poisson distribution Var(y) = mu.function(b) -b[1]/b[2] > ldp <. To find the LD50 estimate we can use a simple function: > ld50 <. its first level is taken as failure (0) and all other levels as `success' (1). If the response is a vector it is assumed to hold binary data. The form of dependence of the variance on the mean is a characteristic of the response distribution. data = kalythos) > fml <. and in practice the major use of this family is to fit surrogate Poisson log-linear models to frequency data.cbind(kalythos$y.ld50(coef(fmp)). so we add a matrix to our data frame: > kalythos$Ymat <. Occasionally genuinely Poisson data arises in practice and in the past it was often analyzed as gaussian data after either a log or a square-root transformation. data = kalythos) Since the logit link is the default the parameter may be omitted on the second call. As a graceful alternative to the latter. family = binomial. incidentally. consider fitting the non-linear regression y = theta_1 z_1 / (z_2 . ldl <. a Poisson generalized linear model may be fitted as in the following example: > fmod <. This is a large and important subject we will not discuss further here.glm(y ~ A + B + x. If the response is a factor . For example. Supposing a suitable data frame to be set up we could fit this non-linear regression as 62 de 99 25/02/2011 10:36 . x_2 = -1/z_1.ld50(coef(fml))..counts) Quasi-likelihood models For all families the variance of the response will depend on the mean and will have the scale parameter as a multiplier.kalythos$y) To fit the models we use > fmp <.

0) nlminb() . 0.1 seem adequate. Here is an example from Bates & Watts (1988). 1. data = biochem) The reader is referred to the manual and the help document for further information.2.05) > yfit <. > plot(x. This method makes sense if the observed errors could have plausibly arisen from a normal distribution. 0. 107. 0.1.7 Nonlinear least squares and maximum likelihood models Certain forms of nonlinear model can be fitted by Generalized Linear Models ( glm() ). guess some parameter values.com/translate_c?hl=pt-BR&ie=UTF-. 1. Next: Some non-standard models . Up: Nonlinear least squares and maximum likelihood models 11. But in the majority of cases we have to approach the nonlinear curve fitting problem as one of nonlinear optimization. Previous: Generalized linear models . 152.seq(.02. 200) The fit criterion to be minimized is: > fn <. nlm() and (from R 2..10. 0.02. To obtain the approximate standard errors (SE) of the estimates we do: 63 de 99 25/02/2011 10:36 . Up: Statistical models in R 11.10) > y <.11. 0. > nlfit <.22. yfit)) We could do better.7. family = quasi(link=inverse. 191. there is no guarantee that the procedure will converge on satisfactory estimates. We seek the parameter values that minimize some index of lack-of-fit. as needed.1). 0. Mínimos quadrados Maximum likelihood Next: Maximum likelihood . p = c(200. 0. variance=constant).nlm(fn. 207. Now do the fit: > out <.1 + xfit) > lines(spline(xfit.11. 201. but these starting values of 200 and 0.06.c(0. 0. and convergence may depend critically upon the quality of the starting values.c(76.56. 0. The data are: > x <. and out$estimate are the least squares estimates of the parameters.06. hessian = TRUE) After the fitting. out$minimum is the SSE.Uma Introdução ao R http://translate. One way to find sensible starting values is to plot the data.1 Least squares One way to fit a nonlinear model is by minimizing the sum of the squared errors (SSE) or residuals.function(p) sum((y . 139. 47.. 97. Previous: Nonlinear least squares and maximum likelihood models .1. y) > xfit <. Unlike linear regression for example. 123.200 * xfit/(0. 1. R's nonlinear optimization routines are optim() . page 51. 159. 0.22. .02. and they do this by trying out various parameter values iteratively.glm(y ~ x1 + x2 .56. All the methods require initial guesses about what parameter values to try.(p[1] * x)/(p[2] + x))^2) In order to do the fit we need initial estimates of the parameters. which provide the functionality (and more) of S-P LUS 's ms() and nlminb() .googleusercontent. and superimpose the model curve using those values.

1.449 > summary(fit) Formula: y ~ SSmicmen(x. y) > xfit <. df) > fit Nonlinear regression model model: y ~ SSmicmen(x. 61.24e-11 K 6.Uma Introdução ao R http://translate. 1.seq(. 59. To obtain the approximate SEs of the estimates 64 de 99 25/02/2011 10:36 .nlm(fn.615 3. 28. 62. 1.96 SE. Vm.281e-03 7. 1. p = c(-50.nls(y ~ SSmicmen(x.6907.8610.02.function(p) sum( . 1.googleusercontent. and out$estimate are the maximum likelihood estimates of the parameters.06412123 residual sum-of-squares: 1195.c(59. Vm.frame(x=x.8369. 1. This example fits a logistic model to dose-response data. 62. out$minimum is the negative log-likelihood. The data are: > x <. K) data: df Vm K 212. 53.947e+00 30. 60) > n <.com/translate_c?hl=pt-BR&ie=UTF-.c(1.(y*(p[1]+p[2]*x) . 56. 1.7. > sqrt(diag(2*out$minimum/(length(y) .127e+02 6. 13.06412146 + xfit) > lines(spline(xfit. so we can use > df <.05) > yfit <. hessian = TRUE) After the fitting. The method finds the parameter values which maximize the log likelihood. . Error t value Pr(>|t|) Vm 2.data. We can superimpose the least squares fit on a new plot: > plot(x.7842. 18. or equivalently which minimize the negative log-likelihood. 63.68370711 0.7651 Previous: Least squares .212.8839) > y <. K) Parâmetros: Estimate Std.412e-02 8. Vm. A 95% confidence interval would be the parameter estimate +/.7552. yfit)) The standard package stats provides much more extensive facilities for fitting non-linear models by least squares.2) * solve(out$hessian))) The 2 in the line above represents the number of parameters. y)) )) We pick sensible starting values and do the fit: > out <. 52.743 1. The model we have just fitted is the Michaelis-Menten model.1.68384222 * xfit/(0. K).2 Maximum likelihood Maximum likelihood is a method of nonlinear model fitting that applies even if the errors are not normal.c( 6..7242. which clearly could also be fit by glm() . 108–111. y=y) > fit <. 60.n*log(1+exp(p[1]+p[2]*x)) + log(choose(n. Up: Nonlinear least squares and maximum likelihood models 11. Here is an example from Dobson (1990).57e-05 Residual standard error: 10.20).. pp. 60) The negative log-likelihood to minimize is: > fn <.8113. 1.1.93 on 10 degrees of freedom Correlation of Parameter Estimates: Vm K 0.

Function lqs in the recommended package MASS provides state-of-art algorithms for highly-resistant fits.1. There are several functions available for fitting regression models in a way resistant to the influence of extreme outliers in the data. Function loess is in the standard package stats . Previous: Statistical models in R . but many other generic functions such as plot() and text() are well adapted to displaying the results of a tree-based model fit in a graphical way. Mixed models. This technique aims to construct a regression function from smooth additive functions of the determining variables. tree-based models seek to bifurcate the data. Tree-based models.8 Some non-standard models We conclude this chapter with just a brief mention of some of the other facilities available in R for special regression and data analysis problems.. Less resistant but statistically more efficient methods are available in packages.googleusercontent.Uma Introdução ao R http://translate. Robust regression. Models are again specified in the ordinary linear model form. recursively. we do: > sqrt(diag(solve(out$hessian))) A 95% confidence interval would be the parameter estimate +/..com/translate_c?hl=pt-BR&ie=UTF-. 65 de 99 25/02/2011 10:36 . Additive models. Rather than seek an explicit global linear model for prediction or interpretation. The loess() function fits a nonparametric regression by using a locally weighted regression. It is possible to use the facilities to display a wide variety of statistical graphs and also to build entirely new types of graph. Next: Packages . Previous: Nonlinear least squares and maximum likelihood models . Up: Top 12 Graphical procedures Graphical facilities are an important and extremely versatile component of the R environment. usually one for each determining variable. that is linear and non-linear regressions in which some of the coefficients correspond to random effects.96 SE. Such regressions are useful for highlighting a trend in messy data or for data reduction to give some insight into a large data set. The model fitting function is tree() . together with code for projection pursuit regression. The results often lead to insights that other data analysis methods tend not to yield. and as heterogeneous as possible between. The recommended nlme package provides functions lme() and nlme() for linear and non-linear mixed-effects models. Functions avas and ace in package acepack and functions bruto and mars in package mda provide some examples of these techniques in user-contributed packages to R. Tree models are available in R via the user-contributed packages rpart and tree . Up: Statistical models in R 11. for example function rlm in package MASS . Local approximating regressions. These functions make heavy use of formulae to specify the models. An extension is Generalized Additive Models . implemented in user-contributed packages gam and mgcv . at critical points of the determining variables in order to partition the data ultimately into groups that are as homogeneous as possible within.

Plotting commands are divided into three basic groups: High-level plotting functions create a new plot on the graphics device. Interactive use is also easy because at startup time R initiates a graphics device driver which opens a special graphics window for the display of interactive graphics.googleusercontent.1. In addition.. Interactive graphics functions allow you interactively add information to. titles and so on. 66 de 99 25/02/2011 10:36 .com/translate_c?hl=pt-BR&ie=UTF-.1 The plot() function One of the most frequently used plotting functions in R is the plot() function. such as extra points. erasing the current plot if necessary.) High-level plotting commands always start a new plot. Low-level plotting functions add more information to an existing plot. The plot() function Displaying multivariate data Display graphics Arguments to high-level plotting functions Next: Displaying multivariate data . axes. or extract information from. R maintains a list of graphical parameters which can be manipulated to customize your plots. it is useful to know that the command used is X11() under UNIX. Where appropriate. possibly with axes. labels.. High-level plotting commands Low-level plotting commands Interacting with graphics Using graphics parameters Graphics parameters Os drivers de dispositivo Dynamic graphics Next: Low-level plotting commands . but in most cases. There is a recommended package lattice which builds on grid and provides ways to produce multi-panel plots akin to those in the Trellis system in S. Previous: High-level plotting commands . Up: High-level plotting commands 12. A separate graphics sub-system in package grid coexists with base – it is more powerful but harder to use. Up: Graphics 12. The graphics facilities can be used in both interactive and batch modes. interactive use is more productive. R plotting commands can be used to produce a variety of graphical displays and to create entirely new kinds of display. Once the device driver is running. windows() under Windows and quartz() under Mac OS X. This is a generic function: the type of plot produced is dependent on the type or class of the first argument. lines and labels. using a pointing device such as a mouse. labels and titles are automatically generated (unless you request otherwise. Although this is done automatically. This manual only describes what are known as `base' graphics. Previous: Graphics .Uma Introdução ao R http://translate.1 High-level plotting commands High-level plotting functions are designed to generate a complete plot of the data passed as arguments to the function. an existing plot.

y ) produces a scatterplot of y against x . that is. then the command > coplot(a ~ b | c) produces a number of scatterplots of a against b for given values of c .1. The first two forms produce distributional plots of the variables in a data frame (first form) or of a number of named objects (second form).. y is a numeric vector. expr is a list of object names separated by ` + ' (eg. the command > pairs(X) produces a pairwise scatterplot matrix of the variables defined by the columns of X .2 Displaying multivariate data R provides two very useful functions for representing multivariate data.. y is any object. If x is a complex vector. every column of X is plotted against every other column of X and the resulting n(n-1) plots are arranged in a matrix with plot scales constant over the rows and columns of the matrix.y) xy ) If x and y are vectors.smooth() . plot( plot( Next: Display graphics . If x is a numeric vector. If c is a factor. When three or four variables are involved a coplot may be more enlightening. plot( f ) plot( f . The number and position of intervals can be controlled with given. The default is points() to produce a scatterplot but by supplying some other low-level graphics function of two vectors x and y as the value of panel= you can produce any type of plot you wish. it is divided into a number of conditioning intervals and for each interval a is plotted against b for values of c within the interval.values= argument to coplot() —the function co. 67 de 99 25/02/2011 10:36 . this produces a time-series plot. You can also use two given variables with a command like > coplot(a ~ b | c + d) which produces scatterplots of a against b for every joint conditioning interval of c and d . If X is a numeric matrix or data frame. the second form produces boxplots of y for each level of f .com/translate_c?hl=pt-BR&ie=UTF-. Up: High-level plotting commands 12. An example panel function useful for coplots is panel. The coplot() and pairs() function both take an argument panel= which can be used to customize the type of plot which appears in each panel. Previous: The plot() function . it produces a plot of the values in the vector against their index in the vector. When c is numeric. The third form plots y against every object named in expr . The first form generates a bar plot of f . this simply means that a is plotted against b for every level of c . The same effect can be produced by supplying one argument (second form) as either a list containing two elements x and y or a two-column matrix. If a and b are numeric vectors and c is a numeric vector or factor object (all of the same length). plot( df ) plot(~ expr ) plot( y ~ expr ) df is a data frame. it produces a plot of imaginary versus real parts of the vector elements. plot( x ) If x is a time series. plot( x .intervals() is useful for selecting intervals.googleusercontent.Uma Introdução ao R http://translate. a + b + c ). x. y ) f is a factor object.

as follows: type="p" Plot individual points (the default) 68 de 99 25/02/2011 10:36 . . z.com/translate_c?hl=pt-BR&ie=UTF-. as follows: add=TRUE Forces the function to act as a low-level graphics function. hist(x) hist(x. the contour plot draws contour lines to represent the value of z .. This will work for many.Uma Introdução ao R http://translate... type= The type= argument controls the type of plot produced. breaks= n) b . Alguns exemplos são: qqnorm(x) qqline(x) qqplot(x.1..googleusercontent.. and the persp plot draws a 3D surface. In a dotchart the y-axis gives a labelling of the data in x and the x-axis gives its value. The third form plots the quantiles of x against those of y to compare their respective distributions. Up: High-level plotting commands 12.. . axes=FALSE Suppresses generation of axes—useful for adding your own custom axes with the axis() function. .) Produces a histogram of the numeric vector x . the breakpoints can be specified exactly with the breaks= argument. but not all. Alternatively.. Next: Arguments to high-level plotting functions . . A sensible number of classes is usually chosen.) image(x. The image plot draws a grid of rectangles using different colours to represent the value of z ... . z. the bars represent relative frequencies divided by bin width instead of counts. superimposing the plot on the current plot (some functions only). y.. axes=TRUE . The first form plots the numeric vector x against the expected Normal order scores (a normal scores plot) and the second adds a straight line to such a plot by drawing a line through the distribution and data quartiles.) contour(x.1.) persp(x.3 Display graphics Other high-level graphics functions produce different types of plots.. but a recommendation can be given with the nclass= argument. y. If the probability=TRUE argument is given. log="x" log="y" log="xy" Causes the x. nclass= hist(x.. Previous: Displaying multivariate data . z. The default. means include axes. y or both axes to be logarithmic. y) Distribution-comparison plots. types of plot. For example it allows easy visual selection of all data entries with values lying in specified ranges. Constructs a dotchart of the data in x . Up: High-level plotting commands 12. dotchart(x. y.4 Arguments to high-level plotting functions There are a number of arguments which may be passed to high-level graphics functions. Previous: Display graphics .) Plots of three variables.

the bottom. y. type="l" Plot lines type="b" Plot points connected by lines ( both ) type="o" Plot points overlaid by lines type="h" Plot vertical lines from points to the zero axis ( high-density ) type="s" type="S" Step-function plots... the top of the vertical defines the point. labels. y .2 Low-level plotting commands Sometimes the high-level plotting functions don't produce exactly the kind of plot you desire. sub= string Sub-title. However axes are still drawn (by default) and the coordinate system is set up according to the data.googleusercontent. type="n" No plotting at all. low-level plotting commands can be used to add extra information (such as points. y) Adds points or connected lines to the current plot. placed just below the x-axis in a smaller font.Uma Introdução ao R http://translate. abline(a. Normally labels is an integer or character vector in which case labels[i] is plotted at point (x[i]. y) lines(x. type="n"). in the second. text(x. Up: Graphics 12. Ideal for creating plots with subsequent low-level graphics functions. lines or text) to the current plot. Note : This function is often used in the sequence > plot(x.) Add text to a plot at points given by x.. string string Axis labels for the x and y axes. y. as specified by the character vector names for the points. y[i]) . b) abline(h= y ) 69 de 99 25/02/2011 10:36 . plot() 's type= argument can also be passed to these functions (and defaults to "p" for points() and "l" for lines() . Use these arguments to change the default labels.. Some of the more useful low-level plotting functions are: points(x. and the text() function supplies special characters. xlab= ylab= Next: Interacting with graphics . usually the names of the objects used in the call to the high-level plotting function. Previous: High-level plotting commands . names) The graphics parameter type="n" suppresses the points but sets up the axes. The default is 1:length(x) .com/translate_c?hl=pt-BR&ie=UTF-.) text(x. . main= string Figure title. In this case. In the first form. y. placed at the top of the plot in a large font.

Where x and y arguments are required.. y ) and (optionally) shade it in with hatch lines. Plotting characters.Uma Introdução ao R http://translate. fill= v ) Colors for filled boxes legend( . col= v ) Colors in which points or lines will be drawn legend( ... are identified with the labels in the character vector legend .2. . axis(side. polygon(x. the following code draws the formula for the Binomial 70 de 99 25/02/2011 10:36 . it is useful to add mathematical symbols and formulae to a plot.. or fill it if the graphics device allows the filling of figures... as follows: legend( . Also lm. y. Mathematical annotation Hershey vector fonts Next: Hershey vector fonts . . Coordinates are given in terms of user coordinates which are defined by the previous high-level graphics command and are chosen based on the supplied data. colors etc. Previous: Low-level plotting commands . abline(v= x ) abline( lm. In this way functions such as locator() (see below) may be used to specify positions on a plot interactively. and tick positions and labels. it is also sufficient to supply a single argument being a list with elements named x and y . y.) Draws a polygon defined by the ordered vertices in ( x . x and y coordinates) to determine where to place the new plot elements. counting clockwise from the bottom. pch= v ) Plotting characters (character vector) title(main.1 Mathematical annotation In some cases. legend(x.obj may be list with a coefficients component of length 2 (such as the result of model-fitting functions. in that order. lwd= v ) Line widths legend( .googleusercontent. or title . and v= x similarly for the x-coordinates for vertical lines.. mtext . This can be achieved in R by specifying an expression rather than a character string in any one of text . Up: Low-level plotting commands 12.) plot in a large font and (optionally) a sub-title Adds an axis to the current plot on the side given by the first argument (1 to 4. At least one other argument v (a vector the same length as legend ) with the corresponding values of the plotting unit must also be given. For example. . lty= v ) Line styles legend( . h= y may be used to specify y-coordinates for the heights of horizontal lines to go across a plot. legend..) which are taken as an intercept and slope.obj ) Adds a line of slope b and intercept a to the current plot.) Adds a legend to the current plot at the specified position. line styles. Useful for adding custom axes after calling plot() with the axes=FALSE argument. Low-level plotting functions usually require some positioning information (eg.com/translate_c?hl=pt-BR&ie=UTF-.) Other arguments control the positioning of the axis within or beside the plot. Similarly a matrix with two columns is also valid input. axis . sub) Adds a title main to the top of the current sub at the bottom in a smaller font..

Hershey fonts provide certain symbols that may not be available in the standard fonts. In particular. It is particularly useful for interactively selecting positions for graphic elements such as legends or labels when it is difficult to calculate in advance where the graphic should be placed.) identify(x. for rotated and/or small text. "Outlier". cartographic symbols and astronomical symbols. there are zodiac signs. type) Waits for the user to select locations on the current plot using the left mouse button. ( locator() will be ignored if the current device. q^{nx}))) More information..Uma Introdução ao R http://translate. This continues until n (default 512) points have been selected. locator() is usually called with no arguments. Hershey fonts provide cyrillic and japanese (Kana and Kanji) characters. including a full listing of the features available can obtained from within R using the commands: > help(plotmath) > example(plotmath) > demo(plotmath) Previous: Mathematical annotation . expression(paste(bgroup("(". to place some informative text near an outlying point. the default is no plotting.googleusercontent. atop(n. including tables of Hershey characters can be obtained from within R using the commands: > help(Hershey) > demo(Hershey) > help(Japanese) > demo(Japanese) Next: Using graphics parameters .2. adj=0) may be useful. For example. especially on a computer screen. The simplest of these is the locator() function: locator(n. p^x. ")"). locator() returns the locations of the points selected as a list with two components x and y . labels) Allow the user to highlight any of the points defined by x and y (using the left mouse 71 de 99 25/02/2011 10:36 .. such as postscript does not support interactive pointing.2 Hershey vector fonts It is possible to specify Hershey vector fonts for rendering text when using the text and contour functions. More information.3 Interacting with graphics R also provides functions which allow users to extract or add information to a plot using a mouse. y. the command > text(locator(1). x). probability function: > text(x. The type argument allows for plotting at the selected points and has the same effect as for high-level graphics commands. There are three reasons for using the Hershey fonts: Hershey fonts can produce better output. or another mouse button is pressed. Up: Graphics 12. Up: Low-level plotting commands 12. Previous: Low-level plotting commands . y.com/translate_c?hl=pt-BR&ie=UTF-.

you could use some informative string (such as a case name) as a highlight by using the labels argument to identify() . Given a number of (x. par() Without arguments.com/translate_c?hl=pt-BR&ie=UTF-. Sometimes we want to identify particular points on a plot. we may wish the user to select some observation of interest from a graphical display and then manipulate that observation in some way.) A separate list of graphics parameters is maintained for each active device. Up: Graphics 12. Graphics parameters can be set in two ways: either permanently. Every graphics parameter has a name (such as ` col '. particularly for presentation or publication purposes.4. R's defaults do not always produce exactly that which is required. Previous: Using graphics parameters . Next: Graphics parameters . identify() returns the indices of the selected points. Returns the indices of the selected points when another button is pressed. lty=2) With named arguments (or a single list argument). If there is a point near the mouse pointer it will be marked with its index number (that is. which controls colors. customize almost every aspect of the display using graphics parameters . and each device has a default set of parameters when initialized. R maintains a list of a large number of graphics parameters which control things such as line style. When the process is terminated (see above).. "lty")) With a character vector argument. figure arrangement and text justification among many others. affecting all graphics functions which access the current device. y) > identify(x.Uma Introdução ao R http://translate.. we could use the identify() function as follows: > plot(x. returns a list of all graphics parameters and their values for the current device. y) The identify() functions performs no plotting itself. You can. button) by plotting the corresponding component of labels nearby (or the index number of the point if labels is absent). affecting only a single graphics function call.1 Permanent changes: The par() function The par() function is used to access and modify the list of graphics parameters for the current graphics device. Alternatively. Previous: Interacting with graphics . as a list. For example. sets the values of the named graphics 72 de 99 25/02/2011 10:36 . The par() function Arguments to graphics functions Next: Arguments to graphics functions . Up: Using graphics parameters 12. however.) and a value (a color number. rather than their positions. returns only the named graphics parameters (again. you can use these indices to extract the selected points from the original vectors x and y .) par(col=4.googleusercontent. colors. or disable marking altogether with the plot = FALSE argument. par(c("col". but simply allows the user to move the mouse pointer and click the left mouse button near a point.4 Using graphics parameters When creating graphics. or temporarily. y) coordinates in two numeric vectors x and y . for example. its position in the x / y vectors) plotted nearby.

. except that the changes only last for the duration of the function call. name is the name of the parameter.2 Temporary changes: Arguments to graphics functions Graphics parameters may also be passed to (almost) any graphics function as named arguments. which will be used by all graphics functions unless an alternative value is given.com/translate_c?hl=pt-BR&ie=UTF-. > par(oldpar) To save and restore all settable 23 graphical parameters use > oldpar <. do some plotting..5 Graphics parameters list The following sections detail many of the commonly-used graphical parameters. This is often undesirable behavior—usually we want to set some graphics parameters. the argument name to use in calls to par() or a graphics function. without changing the default plotting character for future plots. Up: Using graphics parameters 12. Por exemplo: > plot(x. parameters.. Setting graphics parameters with the par() function changes the value of the parameters permanently . Unfortunately. that is. Note that calls to par() always affect the global values of graphics parameters. y... yaxt 73 de 99 25/02/2011 10:36 .readonly=TRUE) . this is not implemented entirely consistently and it is sometimes necessary to set and reset graphics parameters using par() . You can restore the initial values by saving the result of par() when making changes. This has the same effect as passing the arguments to the par() function. and returns the original values of the parameters as a list. > oldpar <. Graphics parameters will be presented in the following form: name = value A description of the parameter's effect. value is a typical value you might use when setting the parameter. Up: Graphics 12. You can think of setting graphics parameters in this way as setting “default” values for the parameters.Uma Introdução ao R http://translate.. plotting commands .. Note that axes is not a graphics parameter but an argument to a few plot methods: see xaxt and . The R help documentation for the par() function provides a more concise summary. and restoring the initial values when plotting is complete. and then restore the original values so as not to affect the user's R session. even when par() is called from within a function. Next: Device drivers . lty=2) . > par(oldpar) Previous: The par() function .par(no. pch="+") produces a scatterplot using a plus sign as the plotting character. Previous: Using graphics parameters .par(col=4. plotting commands ..googleusercontent.4... in the sense that all future calls to graphics functions (on the current device) will be affected by the new value. this is provided as a somewhat more detailed alternative.

respectively.5. Plotted points tend to appear slightly above or below the appropriate position unless you use ". lty=2 Line types. 3 to italic. Not all devices support this. text and polygons (filled regions. 2 to bold face.lab font.axis font. In addition. To see what the symbols are.) Graphical parameters exist which control how these graphical elements are drawn.main font. lwd=2 Line widths. The default varies with graphics drivers. pch = 0:25) Those from 21 to 25 may appear to duplicate earlier symbols.main col. Graphical elements Axes and tick marks Figure margins Multiple figure environment Next: Axes and tick marks . Up: Graphics parameters 12. font.sub The font to be used for axis annotation. The actual value is 74 de 99 25/02/2011 10:36 .1 Graphical elements R plots are made up of points. a specialized plotting symbol is produced. If possible.com/translate_c?hl=pt-BR&ie=UTF-. Affects axis lines as well as lines drawn with lines() . use the command > legend(locator(1). which produces centered points. Previous: Graphics parameters . 0 means left justify.Uma Introdução ao R http://translate. respectively. as follows: pch="+" Character to be used for plotting points. but it is usually a circle. device drivers arrange so that 1 corresponds to plain text. and some have restrictions on the widths that can be used. x and y labels. font=2 An integer which specifies which font to use for text. lines. but can be coloured in different ways: see the help on points and its examples. etc. main and sub-titles. filled regions and images. as. main and sub-titles. or some combination of both. x and y labels. Alternative line styles are not supported on all graphics devices (and vary on those that do) but line type 1 is always a solid line." as the plotting character.lab col. 1 means right justify and 0. lines. line type 0 is always invisible. pch=4 When pch is given as an integer between 0 and 25 inclusive. 4 to bold italic and 5 to a symbol font (which include Greek letters).5 means to center horizontally about the plotting position. and line types 2 and onwards are dotted or dashed lines. A number from the current palette (see ?palette ) or a named colour. Desired width of lines.character(0:25). adj=-0. pch can be a character or a number in the range 32:255 representing a character in the current font. col.sub The color to be used for axis annotation.axis col. text.1 Justification of text relative to the plotting position.googleusercontent. in multiples of the “standard” line width.. col=2 Colors to be used for points..

5. The second component is the distance to the tick labels.lab cex.5) the tick marks on the x and y axes are forced to be the same size. The third number is the desired length of axis labels. Positive numbers measure outside the plot region. etc. Previous: Axes and tick marks .5.3 Figure margins A single plot in R is known as a figure and comprises a plot region surrounded by margins (possibly containing axis labels. xaxs="r" yaxs="i" Axis styles for the x and y axes. 7.) These components can be customized with the following graphics parameters.. in characters (including the decimal point..) Choosing a too-small value for this parameter may result in all tick labels being rounded to the same number! las=1 Orientation of axis labels. tck=0.com/translate_c?hl=pt-BR&ie=UTF-. 1 means always horizontal. the tick marks (which mark off unit divisions along the axis line) and the tick labels (which mark the units. cex. as a fraction of the size of the plotting region.) and (usually) bounded by the axes themselves. Previous: Graphical elements . 0 means always parallel to axis. Next: Figure margins . the proportion of text that appears to the left of the plotting position. A value of 1 gives grid lines. Graphics parameters controlling figure layout include: 75 de 99 25/02/2011 10:36 . Negative values give tick marks outside the plotting region. Up: Graphics parameters 12.sub The character expansion to be used for axis annotation. When tck is small (less than 0. (S has other styles not implemented in R.main cex.1 leaves a gap of 10% of the text width between the text and the plotting position. Use tck=0. mgp=c(3. Up: Graphics parameters 12. x and y labels.-1. The first component is the distance from the axis label to the axis position.axis cex. respectively. The value is the desired size of text characters (including plotting characters) relative to the default text size.) Next: Multiple figure environment . and you can construct axes yourself with the low-level axis() graphics function. respectively. 0) Positions of axis components. cex=1. negative numbers inside. so a value of -0.Uma Introdução ao R http://translate. however style "r" leaves a small amount of space at the edges.01 Length of tick marks. 12) The first two numbers are the desired number of tick intervals on the x and y axes respectively.5 Character expansion.googleusercontent.2 Axes and tick marks Many of R's high-level plots have axes. titles. Axes have three main components: the axis line (line style controlled by the lty graphics parameter).01 and mgp=c(1. in text lines.5. 1. lab=c(5. main and sub-titles. and the final component is the distance from the axis position to the axis line (usually zero). With styles "i" (internal) and "r" (the default) tick marks always fall within the range of the data. and 2 means always perpendicular to the axis.0) for internal tick marks.

mar=c(4.4 Multiple figure environment R allows you to create an n by m array of figures on a single page. Set this parameter to jump between figures in the array. 0) Size of outer margins.. 4) Set the size of a multiple figure array. 9.googleusercontent.. In a layout with exactly two rows and columns the base size is reduced by a factor of 0. 3. and mai are equivalent in the sense that setting one changes the value of the other. measured in inches. The default values chosen for this parameter are often too large. the first measures in text lines and the second in inches. Like mar and mai . 0) Widths of the bottom. the last two are the number of rows and columns in the multiple figure array. as shown in the following figure.com/translate_c?hl=pt-BR&ie=UTF-. right. 0. 2. 4)/10 Position of the current figure on the page. The layout in the Figure could have been created by setting mfrow=c(3.66. Setting either of these can reduce the base size of symbols and text (controlled by par("cex") and the pointsize of the device). the second is the number of columns. The example value would be for a figure in the bottom right of the page. The graphical parameters relating to multiple figures are as follows: mfcol=c(3.5. oma=c(2. however this may not be enough when many figures share the same page. Set this parameter for arbitrary positioning of figures within a page. When multiple figures are in use (see below) the margins are reduced. 2. starting with the bottom margin and working clockwise. The first two numbers are the row and column of the current figure. as a percentage of the page measured from the bottom left corner. You can even use different values for the last two numbers than the true values for unequally-sized figures on the same page. 0. 0.5. 0. 3. the reduction factor is 0. 2.Uma Introdução ao R http://translate.2) . The bottom and left margins must be large enough to accommodate the axis and tick labels. Values are the positions of the left. fig=c(4. mar except the measurement unit is text lines. the right-hand margin is rarely needed. mai=c(1.8. The only difference between these two parameters is that setting mfcol causes figures to be filled by column. mfrow fills by rows. 2) Position of the current figure in a multiple figure environment. Each figure has its own margins. using the postscript() driver with the height=4 argument will result in a plot which is about 50% margin unless mar or mai are set explicitly. The first value is the number of rows. the default is chosen without regard to the size of the device surface: for example.5. mfg=c(2. 1) Similar to mai . respectively. 0) omi=c(0. the figure shows the page after four plots have been drawn. top and right margins.83: if there are three or more of either rows or columns. and the array of figures is optionally surrounded by an outer margin . use new=TRUE as well (unlike S). If you want to add a figure to a current page. 76 de 99 25/02/2011 10:36 . bottom and top edges respectively. Previous: Figure margins . left. 0. Furthermore. 2) mfrow=c(2. 1. and neither is the top margin if no title is being used. Up: Graphics parameters 12.

Text can be added to the outer margins with the mtext() function with argument outer=TRUE .) jpeg() Produces a bitmap JPEG file. For example. Up: Graphics 12.) PostScript diagrams for typeset documents Multiple graphics devices Next: Multiple graphics devices . Outer margins are particularly useful for page-wise titles. There are no outer margins by default.6. be sure to terminate the device driver by issuing the command > dev.com/translate_c?hl=pt-BR&ie=UTF-. (This will happen automatically at the normal end of a session. Some commonly-used device drivers are: X11() For use with the X11 window system on Unix-alikes windows() For use on Windows quartz() For use on Mac OS X postscript() For printing on PostScript printers.screen() and layout() functions. Before this can begin. More complicated arrangements of multiple figures can be produced by the split. (Not always available: see its help page. Up: Device drivers 12. Previous: Device drivers .) When you have finished with a device. pdf() Produces a PDF file. or creating PostScript graphics files. Next: Dynamic graphics . (Not always available: see its help page.” for example) into a form that the particular device can understand.off() This ensures that the device finishes cleanly.. for example in the case of hardcopy devices this ensures that every page is completed and has been sent to the printer. There is one such function for every device driver: type help(Devices) for a list of them all. which can also be included into PDF files. This is done by starting a device driver . etc. R needs to be informed what type of device it is dealing with.1 PostScript diagrams for typeset documents 77 de 99 25/02/2011 10:36 .. Device drivers are started by calling a device driver function. issuing the command > postscript() causes all future graphics output to be sent to the printer in PostScript format. however. so you must create them explicitly using oma or omi .Uma Introdução ao R http://translate. The purpose of a device driver is to convert graphical instructions from R (“draw a line. Previous: Graphics parameters . png() Produces a bitmap PNG file.googleusercontent. however.6 Device drivers R can generate graphics (of varying levels of quality) on almost any type of display or printing device. as well as by the grid and lattice packages. best used for image plots.

metafile() [Windows] quartz() [Mac OS X] postscript() pdf() png() jpeg() tiff() bitmap() .. The device at position 1 on the list is always the null device which does not accept graphics commands at all. dev. onefile=FALSE. but only marks the output as such when the onefile=FALSE argument is supplied. Of course only one graphics device can accept graphics commands at any one time... This is the case even if the file was only created earlier in the same R session. width=6. height=8.printer() win. perhaps for inclusion in a document. and their meanings are as follows: X11() [UNIX] windows() win. Many usages of PostScript output will be to incorporate the figure in another document.googleusercontent.prev() Returns the number and name of the graphics device next to. it will be overwritten. dev. Thus to produce a plot for inclusion use something like > postscript("plot1. and you can control the size of the graphic with the width and height arguments (the plot will be scaled as appropriate to fit these dimensions.com/translate_c?hl=pt-BR&ie=UTF-. or previous to the current device. Each new call to a device driver function opens a new graphics device. horizontal=FALSE. and this is known as the current device . horizontal=FALSE. When multiple devices are open. to which graphics output will be sent. By passing the file argument to the postscript() device driver function. height=5.) For example. This unusual notation stems from S-compatibility: it really means that the output will be a single page (which is part of the EPSF specification). It is important to note that if the file named in the command already exists.eps".list() Returns the number and name of all active devices.Uma Introdução ao R http://translate. thus extending by one the device list. Up: Device drivers 12. the command > postscript("file. respectively.2 Multiple graphics devices In advanced use of R it is often useful to have several graphics devices in use at the same time. they form a numbered sequence with names giving the kind of device at any position.6.next() dev. The main commands used for operating with multiple devices. This device becomes the current device.. pointsize=10) will produce a file containing PostScript code for a figure five inches high. This works best when encapsulated PostScript is produced: R always produces conformant output. you may store the graphics in PostScript format in a file of your choice. The plot will be in landscape orientation unless the horizontal=FALSE argument is given. 78 de 99 25/02/2011 10:36 . pointsize=10) Previous: PostScript diagrams for typeset documents .ps".

org/ and these can be accessed from R via the package rggobi .ggobi. such as printing hardcopies. see Installing packages ) to install and update packages.. are immediately performed. This is done both for efficiency (the full list would take more memory and would take longer to search than a subset). depending on how the device was initiated. which= k ) Make a copy of the device k . such as postscript . such as postscript devices. Next: A sample session .Uma Introdução ao R http://translate. dev. '. dev. The process of developing packages is described in Creating R packages . k) Can be used to change the current graphics device to the one at position k of the device list. Cook and Buja available from http://www. Up: Graphics 12.off() Terminate all graphics devices on the list.set(which= graphics.. use 79 de 99 25/02/2011 10:36 . .com/translate_c?hl=pt-BR&ie=UTF-. eg rotating point clouds or to “brushing” (interactively highlighting) points. However.. To see which packages are currently loaded. Previous: Device drivers . extensive dynamic graphics facilities are available in the system GGobi by Swayne. specified by ' . this will either print the file immediately or correctly complete the file for later printing. Also. Up: Top 13 Packages All R functions and datasets are stored in packages . Returns the number and label of the device. dev.. which= k ) dev. who are protected from name clashes with other code. For some devices.. the boot package containing functions from Davison & Hinkley (1997)). with extra arguments... except the null device.print is similar. To see which packages are installed at your site.off( k ) Terminate the graphics device at point k of the device list. so that end actions. but the copied device is immediately closed. . Here.packages() and update.org /rggobi .7 Dynamic graphics R does not have builtin capabilities for dynamic or interactive graphics. package rgl provides ways to interact with 3D plots. we will describe them from a user's point of view.googleusercontent.copy(device. Previous: Graphics . issue the command > library() with no arguments. Here device is a device function. if needed... for example of surfaces. use a command like > library(boot) Users connected to the Internet can use the install. Only when a package is loaded are its contents available. dev.ggobi.. described at http://www. and to aid package developers.packages() functions (available through the Packages menu in the Windows and RAqua GUIs.print(device. To load a particular package (eg.

2 Contributed packages and CRAN There are hundreds of contributed packages for R. Most are available for download from CRAN ( http://CRAN. because it is defined in the base package. and other repositories such as Bioconductor ( http://www.. Previous: Standard packages .org/ and its mirrors). > search() to display the search list. Some packages may be loaded but not available on the search list (see Namespaces ): these will be included in the list given by > loadedNamespaces() To see a list of all available help topics in an installed package. Previous: Contributed packages and CRAN . Namespaces do three things: they allow the package writer to hide functions and data that are meant only for internal use. and others are designed to complement textbooks.googleusercontent. and currently all of the base and recommended packages do except the datasets package. For example. 80 de 99 25/02/2011 10:36 . and breaking every function that tries to transpose a matrix. The R FAQ contains a list that was current at the time of release.com/translate_c?hl=pt-BR&ie=UTF-.start () to start the HTML help system. The double-colon operator :: selects definitions from a particular namespace. Only functions that are exported from the package can be retrieved in this way. Some of these packages implement specialized statistical methods.bioconductor. Namespaces prevent the user's definition from taking precedence.org/ ). They contain the basic functions that allow R to work. In the example above.R-project.3 Namespaces Packages can have namespaces . written by many different authors. and the datasets and standard statistical and graphical functions that are described in this manual.1 Standard packages The standard (or base ) packages are considered part of the R source code. They should be automatically available in any R installation. and they provide a way to refer to an object within a particular package.Uma Introdução ao R http://translate. Previous: Packages . pacotes padrão Contributed packages and CRAN Namespaces Next: Contributed packages and CRAN . for a complete list.. See R packages . Up: Packages 13. Up: Packages 13. but the collection of available packages changes frequently. they prevent functions from breaking when a user (or other package writer) picks a name that clashes with one in the package. and then navigate to the package listing in the Reference section. Next: Namespaces . others give access to data or hardware. but users might define their own function named t . t() is the transpose function in R. use > Help. There are two operators that work with namespaces. Up: Packages 13. the transpose function will always be available as base::t . Some (the recommended packages) are distributed with every binary distribution of R.

data=dummy.Uma Introdução ao R http://translate. 2.start() Start the HTML interface to on-line help (using a web browser available at your machine).lm(y ~ x.com/translate_c?hl=pt-BR&ie=UTF-.1 + sqrt(x)/2 . $ R Start R as appropriate for your platform. Next: Invoking R . which searches multiple packages. You should briefly explore the features of this facility with the mouse. A `weight' vector of standard deviations. y= x + rnorm(x)*w) dummy Make a data frame of two columns.. A graphics window will appear automatically. with a banner. attach(dummy) 81 de 99 25/02/2011 10:36 . fm <. and loading one may cause others to be automatically loaded. weight=1/w^2) summary(fm1) Since we know the standard deviations. The R program begins. Login. Many features of the system will be unfamiliar and puzzling at first. ls() See which R objects are now in the R workspace. x and y. we can do a weighted regression.googleusercontent. With y to the left of the tilde. w <....rnorm(50) y <. start your windowing system. . Iconify the help window and move on to the next part. The triple-colon operator ::: may be seen in a few places in R code: it acts like the double-colon operator but also allows access to hidden objects. plot(x. Users are more likely to use the getAnywhere() function. y) Plot the points in the plane.1:20 Make x = (1. The colon operators described above will also cause automatic loading of the associated package. Packages are often inter-dependent.frame(x=x.data. rm(x. x <. and look at it. When packages with namespaces are loaded automatically they are not added to the search list.and y-coordinates. Previous: Packages .) help.rnorm(x) Generate two pseudo-random normal vectors of x. but this puzzlement will soon disappear. we are modelling y dependent on x. y) Remove objects no longer needed. fm1 <.lm(y ~ x. Up: Top Appendix AA sample session The following session is intended to introduce to you some features of the R environment by using them. dummy <. (Clean up). x <. data=dummy) summary(fm) Fit a simple linear regression and look at the analysis. 20). the prompt on the left hand side will not be shown to avoid confusion. (Within R.

Run) anova(fm0. xlab="Fitted values" . . . There are five experiments (column Expt ) and each has 20 runs (column Run ) and sl is the recorded speed of light. This dataset is available in the morley object. plot(x. 82 de 99 25/02/2011 10:36 .tab" . Speed.aov(Speed ~ Run + Expt. The next section will look at data from the classical experiment of Michaelson and Morley to measure the speed of light.file("data". "morley. plot(Expt. ylab="Residuals" . fm <. ylab="Residuals" . lty=3) The true regression line: (intercept 0. but we will read it to illustrate the read. package="datasets") filepath Get the path to the data file. resid(fm).Uma Introdução ao R http://translate.factor(mm$Expt) mm$Run <. filepath <. dummy) Clean up again.factor(mm$Run) Change Expt and Run into attach(mm) factors. col = "red") Weighted regression line. suitably coded. slope 1). Você pode vê-lo? qqnorm(resid(fm). file.system. fm1. fm) Fit the sub-model omitting `runs'. and compare using a formal analysis of variance.lowess(x. xlab="Fitted values" .show(filepath) Opcional. y) Make a nonparametric local regression function. ~ . lrf. mm <. (Not very useful here. fm0) Clean up before moving on.. abline(coef(fm1).table function. kurtosis and outliers.com/translate_c?hl=pt-BR&ie=UTF-.. data=mm) summary(fm) Analyze as a randomized block.read. abline(0.table(filepath) mm Read in the Michaelson and Morley data as a data frame.") Compare the five experiments with simple boxplots. Look at the file. lrf$y) Add in the local regression. 1. plot(fitted(fm). main="Residuals vs Fitted") A standard regression diagnostic plot to check for heteroscedasticity. and look at it. lines(x. Make the data frame visible at position 3 (the default). main="Residuals Rankit Plot") A normal scores plot to check for skewness.) rm(fm. lrf <. Make the columns in the data frame visible as variables. main="Speed of Light Data". x. y) Standard point plot. mm$Expt <.update(fm. abline(coef(fm)) Unweighted regression line. detach() Remove data frame from the search path.googleusercontent. xlab="Experiment No. with `runs' and `experiments' as factors. detach() rm(fm. fm0 <.

.rnorm(100) + rnorm(100)*1i Suppose we want to sample points within the unit circle. of values of the function cos(y)/(1 + x^2).par(no. th <.1). you probably do not want to save it.seq(-pi. with rows and columns indexed by x and y respectively. R can do complex arithmetic. rm(x.1).. f <. q() Quit the R program. y. type="l") Plotting complex arguments means plot imaginary versus real parts. (of which you can get hardcopies if you wish). par(pty="s") plot(z. plot(w. w <. and restore the old graphics parameters. y. contour(x. nlevels=15. This should be a circle.outer(x. but the distribution is not uniform. You will be asked if you want to save the R workspace. 1/w.xlab="x".readonly = TRUE) par(pty="s") Save the plotting parameters and set the plotting region to “square”. f. oldpar <.googleusercontent.1). w <. y. pch="+". y.(ft(f))/2 fa is the “asymmetric part” of f. rm(th. .. len=100) z <.. par(oldpar) . y is the same. pi].. pi.. y. function(x. image(x.. Previous: A sample session . We now look at some more graphical features: contour and image plots. Up: Top 83 de 99 25/02/2011 10:36 .. objects(). The points should now look more evenly spaced over the disc.. xlim=c(-1. y. fa) Make some high density image plots. ylab="y") lines(z) All points are inside the unit circle. pi. fa.. nlevels=15) Make a contour plot. f) image(x.. add in more lines for more detail. w) . One method would be to take complex numbers with standard normal real and imaginary parts . xlab="x".com/translate_c?hl=pt-BR&ie=UTF-. pch="+".sqrt(runif(100))*exp(2*pi*runif(100)*1i) plot(w. f. y) cos(y)/(1 + x^2)) f is a square matrix. y. z) Clean up again. xlim=c(-1. and to map any outside the circle onto their reciprocal. and clean up before moving on. Next: The command-line editor .. x <. contour(x.. len=50) y <. ( t() is transpose).1). ylab="y") lines(z) The second method uses the uniform distribution.exp(1i*th) 1i is used for the complex number i. add=TRUE) Make a contour map of f.x x is a vector of 50 equally spaced values in the interval [-pi\. w <. fa <.ifelse(Mod(w) > 1.Uma Introdução ao R http://translate.. ylim=c(-1. ylim=c(-1. also. and for an exploratory session like this. . fa) .seq(-pi. f) contour(x. w.

R_PRINTCMD (the default print command) and R_LIBS (specifies the list of R library trees searched for add-on packages).site is used if this exists. or reside in . Most options control what happens at the beginning and at the end of an R session. 84 de 99 25/02/2011 10:36 . The startup mechanism is as follows (see also the on-line help for topic ' Startup ' for more information. or. Then. via the R CMD interface. files . as a wrapper to various R tools (eg. Users will not normally need to use these unless they are trying to limit the amount of memory used by R.First exists. it is executed. if a function . The name of the site file is the one pointed to by the environment variable R_ENVIRON . R searches for user and site files to process for setting environment variables. and the section below for some Windows-specific details). The user file is the one pointed to by the environment variable R_ENVIRON_USER if this is set.1 Invoking R from the command line When working in UNIX or at a command line in Windows. Up: Invoking R B.Uma Introdução ao R http://translate. for processing files in R documentation format or manipulating add-on packages) which are not intended to be called “directly”.Renviron in the current or in the user's home directory (in that order) are searched for.site is used (if it exists). Finally. The name of this file is taken from the environment variable R_PROFILE_USER . the command ' R ' can be used both for starting the main R program in the form R [ options ] [ < infile ] [ > outfile ].Rprofile in the current directory or in the user's home directory (in that order) is searched for. (See help("Startup") for a precise description.) Variables you might want to set include R_PAPERSIZE (the default paper size)..googleusercontent.RData . if unset. R_HOME /etc/Renviron. This function (as well as .. Then R searches for the site-wide startup profile unless the command line option --no-site-file was given.com/translate_c?hl=pt-BR&ie=UTF-.Last which is executed at the end of the R session) can be defined in the appropriate startup profiles.RData if there is one (unless --no-restore or --no-restore-data was specified). unless --no-init-file was given. These files should contain lines of the form ' name = value '. If that variable is unset. there are options for controlling the memory available to the R process (see the on-line help for topic ' Memory ' for more information). It also loads a saved image from . Previous: Invoking R . The name of this file is taken from the value of the R_PROFILE environment variable. the default R_HOME /etc/Rprofile. R searches for a user profile and sources it. otherwise. You need to ensure that either the environment variable TMPDIR is unset or it points to a valid place to create temporary files and directories. a file called . Appendix B Invoking R Invoking R from the command line Invoking R under Windows Invoking R under Mac OS X Scripting with R Next: Invoking R under Windows . if this is unset. In addition. R accepts the following command-line options. Unless --no-environ was given.

This option also affects tilde-expansion: see the help for path.com/translate_c?hl=pt-BR&ie=UTF-. One or more -e options can be used.googleusercontent. ( --no-restore implies all the specific --no-restore-* options. etc. --encoding= enc Specify the encoding to be assumed for input from the console or stdin . --min-vsize= N --max-vsize= N 85 de 99 25/02/2011 10:36 . -f file --file= file Take input from file : ' . but can be set by the environment variable R_HISTFILE ) should be restored at startup or not. This needs to be an encoding known to iconv : see its help page.' means stdin .Uma Introdução ao R http://translate. (There is a limit of 10. --no-environ . Under Windows.) --no-restore-history Control whether the history file (normally file .) RHOME Print the path to the R “home directory” to standard output and exit successfully. --no-environ Do not read any user file to set environment variables. --version Print version information to standard output and exit successfully. Command-line editing is enabled by default interactive use (see --interactive ).000 bytes on the total length of expressions used in this way. R installation puts everything (executables. --no-init-file and --no-restore . -e expression Use expression as an input line.Rhistory in the directory where R was started. --help -h Print short help message to standard output and exit successfully. for more information. The default is to restore. The default is to restore. --no-site-file Do not read the site-wide profile at startup. packages. in non-interactive use one of these must be specified or implied by some other option (see below). This is useful when running R from within Emacs using the ESS (“Emacs Speaks Statistics”) package. --no-init-file Do not read the user's profile at startup.) --no-readline (UNIX only) Turn off command-line editing via readline . --save --no-save Control whether data sets should be saved or not at the end of the R session. the user is asked for the desired behavior when ending the session with q() . Implies --no-save unless --save has been set.expand . --vanilla Combine --no-save .) into this directory. See The command-line editor ..RData in the directory where R was started) should be restored at startup or not. --no-site-file . ( --encoding enc is also accepted. Implies --no-save unless --save has been set. If neither is given in an interactive session. --no-Rconsole (Windows only) Prevent loading the Rconsole file at startup. Apart from the front-end shell script and the man page. --restore --no-restore --no-restore-data Control whether saved images (file . this also includes --no-Rconsole .. but not together with -f or --file .

or regular `kilo' (1000). This defaults to 10000. This option is intended to support programs which use R to compute results for them. --quiet --silent -q Do not print out the initial copyright and welcome messages. and usually 56 bytes on a 64-bit machine. --ess (Windows only) Set Rterm up for use by R-inferior-mode in ESS . R code uses this option to control the printing of diagnostic messages. --interactive (UNIX only) Assert that R really is being run interactively even if input has been redirected: use if input is from a FIFO or pipe and fed from an interactive program. Here. Note that input and output can be redirected in the usual way (using ' < ' and ' > '). A cons cell takes 28 bytes on a 32-bit machine.. Currently. --verbose Print more information about progress. and must be between 32Mb and the maximum allowed on that version of Windows.com/translate_c?hl=pt-BR&ie=UTF-. provided that ' Tcl/Tk ' support is available. `Mega' (2^20). ' M '. but can be increased to allow large and complicated calculations to be done. and in particular set R's option verbose to TRUE . ' Tk '. --min-nsize= N --max-nsize= N Specify the amount of memory used for fixed size objects by setting the number of “cons cells” to N . --gui= type -g type (UNIX only) Use type as graphical user interface (note that this also includes interactive graphics). but the line length limit of 4095 bytes still applies. Warning and error messages are sent to the error channel ( stderr ). Currently the maximum value accepted is 100000. (The default is to deduce that R is being run interactively if and only if stdin is connected to a terminal or pty . For most debuggers (the exceptions are valgrind and recent versions of gdb ). --max-ppsize= N Specify the maximum size of the pointer protection stack as N locations. including asserting interactive use without the command-line editor. --debugger= name -d name (UNIX only) Run R through debugger name . Specify the minimum or maximum amount of memory used for variable size objects by setting the “vector heap” size to N bytes. This is set by default to the smaller of 1. (For back-compatibility. (computer) `Kilo' (2^10). further command line options are disregarded. or ' k '. and should instead be given when starting the R executable from inside the debugger.. N must either be an integer or an integer ending with ' G '.googleusercontent. ' x11 ' and ' tk ' are accepted. -f or --file asserts non-interactive use even if --interactive is given. ' K '. --max-mem-size= N (Windows only) Specify a limit for the amount of memory to be used both for R objects and working areas.5Gb 24 and the amount of physical RAM in the machine.) --args This flag does nothing except cause the rest of the command line to be skipped: this can be useful to retrieve values from it with commandArgs(TRUE) .) Using -e . possible values for type are ' X11 ' (the default) and. 86 de 99 25/02/2011 10:36 . --slave Make R run as quietly as possible. meaning `Giga' (2^30). It implies --quiet and --no-save . See the previous option for details on N .Uma Introdução ao R http://translate.

COMPILE (UNIX only) Compile files for use with R. R. Currently.Uma Introdução ao R http://translate.. including HTML . but not intended to be called “directly”. 87 de 99 25/02/2011 10:36 . The command R CMD allows the invocation of various tools which are useful in conjunction with R. A forma geral é R CMD command args where command is the name of the tool and args the arguments passed on to it. and Rd files open (Windows only) Open a file via Windows' file associations texify (Windows only) Process (La)TeX files with R's style files Use R CMD command --help to obtain usage information for each of the tools accessible via the R CMD interface. package) add-on packages. Rd2pdf can be used as shorthand for Rd2dvi --pdf . LINK (UNIX only) Front-end for creating executable programs. check Check add-on packages. and extracting the examples. the following tools are available.googleusercontent. Rprof Post-process R profiling files.com/translate_c?hl=pt-BR&ie=UTF-. build Build (that is. Rd2txt can be used as shorthand for Rd2conv -t txt .. SHLIB Build shared library for dynamic loading. INSTALL Install add-on packages. Rdconv Rd2txt Convert Rd format to various other formats. Stangle Extract S/R code from Sweave documentation Sweave Process Sweave documentation Rdiff Diff R output ignoring headers etc config Obtain configuration information javareconf (Unix only) Update the Java configuration variables rtags (Unix only) Create Emacs-style tag files from C. LaTeX. Rd2dvi Rd2pdf Convert Rd format to DVI/PDF. REMOVE Remove add-on packages. plain text. BATCH Run R in batch mode.

Failing all those. For example.2 Invoking R under Windows There are two ways to run R under Windows. If that fails.exe . for example to run ldd or pdflatex .exe or a more capable shell). The command-line setting overrides the setting in the user's Rconsole file. --mdi --sdi --no-mdi Control whether Rgui will operate as an MDI program (with multiple child windows within one main window) or an SDI application (with multiple top-level windows for the console. Previous: Invoking R from the command line .. if 88 de 99 25/02/2011 10:36 .pl file.exe ). It first tries to use the Windows "personal" directory (typically C:\Documents and Settings\username\My Documents in Windows XP). You need to ensure that either the environment variables TMPDIR . (These are principally intended for batch use. you can use R CMD cmd args for any other executable cmd on the path: this is useful to have the same environment as R or the specific commands run under. In addition.googleusercontent. PATH . (This mechanism is used for drag-and-drop and file association with RGui. Under Windows with R CMD you may also specify your own .exe .Uma Introdução ao R http://translate.) The following additional command-line options are available when invoking RGui. the methods described in the previous section may be used.exe . After those two user-controllable settings. The startup procedure under Windows is very similar to that under UNIX.sh or .exe .exe or more directly by Rterm. R tries to find system defined home directories. Environment variables can be supplied as ' name = value ' pairs on the command line. graphics and pager). .com/translate_c?hl=pt-BR&ie=UTF-.exe .. and environment variables HOMEDRIVE and HOMEPATH are defined (and they normally are) these define the home directory. It will be run under the appropriate interpreter (Perl for . BSTINPUTS and TEXINPUTS .pl ) with several environment variables set appropriately. the home directory is taken to be the starting directory. but references to the `home directory' need to be clarified. TMP and TEMP are either unset or one of them points to a valid place to create temporary files and directories. If the named file does not exist it sets the working directory if the parent directory exists. as this is not always defined on Windows.RData (in any case) it is interpreted as the path to the workspace to be restored: it implies --restore and sets the working directory to the parent of the named file. Next: Invoking R under Mac OS X . Next.) For interactive use. or if it has extension . that gives the home directory. if the environment variable HOME is defined.bat .pl the appropriate interpreter (if available) is called to run it. If there is an argument ending . that gives the home directory. Up: Invoking R B. including R_HOME . Under Windows cmd can be an executable or a batch file. Within a terminal window (eg cmd. but also works for Rterm. If the environment variable R_USER is defined. R_OSTYPE . and trigger a break to the debugger during command line processing. .Debug Enable the “Break to debugger” menu item in Rgui . invoking by R.sh or . . there is a console-based GUI ( Rgui.

then R CMD latex. It is a standard doubleclickable Mac OS X application. q(status=<exit status code>) If this is entered into a text file runfoo and this is made executable (by chmod 755 runfoo ). You can pass parameters to scripts via additional arguments on the command line: for example R CMD BATCH --args arg1 arg2 foo. Up: Invoking R B. Within a Terminal.R & will pass arguments to a script which can be retrieved as a character vector by args <. The `home directory' is the one inside the R.app ) that by default is installed in the Applications folder on your system. If you want to run this in the background or as a batch job use OS-specific facilities to do so: for example in most shells on Unix-alike OSes R CMD BATCH foo. with the path to R's share/texmf macros appended to TEXINPUTS . Previous: Invoking R under Windows .4 Scripting with R If you just want to run a file foo. and in some Windows shells) #! /path/to/Rscript args <.) Next: Scripting with R . the methods described in the first subsection apply. There is also console-based GUI ( R.. The startup procedure under Mac OS X is very similar to that under UNIX..R & runs a background job.com/translate_c?hl=pt-BR&ie=UTF-. it can be invoked for different arguments by runfoo arg1 arg2 For further options see help("Rscript") . you already have latex.Uma Introdução ao R http://translate.commandArgs(TRUE) . the recommended way is to use R CMD BATCH foo. but the startup and current working directory are set as the user's home directory unless a different startup directory is given in the Preferences window accessible from within the GUI.3 Invoking R under Mac OS X There are two ways to run R under Mac OS X.googleusercontent.commandArgs(TRUE) This is made simpler by the alternative front-end Rscript .exe on your path..exe mydoc will run LaTeX on mydoc.app window by invoking R .R . 89 de 99 25/02/2011 10:36 . This writes R output to stdout and stderr . which can be invoked by Rscript foo. Up: Invoking R B.. but R CMD texify mydoc will work in that case.R arg1 arg2 and this can also be used to write executable script files like (at least on Unix-alikes. (Unfortunately.tex .framework.R of R commands. and this can be redirected in the usual way for the shell running the command. this does not help with the MiKTeX build of LaTeX. Previous: Invoking R under Mac OS X .

Many of these use either Control or Meta characters.40 2..28 3.com/translate_c?hl=pt-BR&ie=UTF-.70 2.03 28. EOF but here stdin() refers to the program source and "stdin" will not be usable..Uma Introdução ao R http://translate. are typed by holding down <META> 26 and pressing <b>.. Note that other versions of readline exist and may be used by the inbuilt command line editor: this used to happen on Mac OS X.40 2..80 2.70 3. It is commonplace to write R scripts with segments like chem <. an inbuilt command line editor allowing recall.90 3. At least in Bourne and bash shells. use #! /usr/bin/env Rscript . to enter Mb .. you could type <ESC><b>. If your terminal does not have a <META> key enabled.60 3.77 3.1 Preliminaries When the GNU readline library is available at the time R is configured for compilation under UNIX. If you do not wish to hardcode the path to Rscript but have it in your path (which is normally the case for an installed R except on Windows).) . and written as Mb in the following.scan(n=24) 2. One thing to consider is what stdin() refers to. Windows versions of R have somewhat simpler command-line editing: see ' Console ' under the ' Help ' menu of the GUI .50 3. If you want to refer to the process's stdin . use "stdin" as a file connection.40 2. Next: Function and variable index .37 3. the functions described below are available.googleusercontent... When using R with readline capabilities.10 3. and the file README. It can be disabled (useful for usage with ESS 25 ) using the startup option --no-readline . Meta characters. such as Meta-b .40 3. Previous: Invoking R . such as Control-m .70 and stdin() refers to the script file to allow such traditional usage. are obtained by holding the <CTRL> down while you press the <m> key. Up: Top Appendix C The command-line editor C. you can still type Meta characters using two-character sequences starting with ESC .20 5.exe . the #! mechanism does not allow extra arguments like #! /usr/bin/env Rscript --vanilla . Thus. Very short scripts can be passed to Rscript on the command-line via the -e flag.70 3.03 3. Another way to write executable script files (suggested by François Pinard) is to use a here document like #! / Bin / sh [environment variables can be set here] R --slave [other options] <<EOF R program goes here. eg scan("stdin".70 2. The ESC character sequences are also allowed on terminals 90 de 99 25/02/2011 10:36 . editing and re-submission of prior commands is used..20 3. Control characters.50 2. . and are written as Cm below.Rterm for command-line editing under Rterm.40 3.95 3.

Cr text Find the last command with the text string in it. Horizontal motion of the cursor Ca Go to the beginning of the command.googleusercontent. Cn Go to the next command (forwards in the history). 91 de 99 25/02/2011 10:36 . Mf Go forward one word.3 Command-line editor summary Command recall and vertical motion Cp Go to the previous command (backwards in the history). Go forward one character. with real Meta keys. On most terminals. Other editing actions are summarized in the following table. Ce Go to the end of the line. Cb Go back one character. On most terminals. respectively. Pressing the <RET> command at any time causes the command to be re-submitted..2 Editing actions The R program keeps a history of the command lines you type. text Append text after the cursor. Cf. displacing any characters to the right of the cursor. you can also use the left and right arrow keys instead of Cb and Cf . In vi mode character insertion mode is started by Mi or Ma ..Uma Introdução ao R http://translate. Note that case is significant for Meta characters. you can also use the up and down arrow keys instead of Cp and Cn . characters are typed and insertion mode is finished by typing a further <ESC>. In Emacs-style command-line editing any straight typing you do while in this editing phase causes the characters to be inserted in the command you are editing. changed if necessary. C. C. and commands in your history may be recalled. including the erroneous lines. and re-submitted as new commands.com/translate_c?hl=pt-BR&ie=UTF-. <DEL> Cd Delete the character under the cursor. respectively. Editing and re-submission texto Cf Insert text at the cursor. Delete the previous character (left of the cursor). Mb Go back one word.

: Scope <= : Logical vectors == : Logical vectors > : Logical vectors >= : Logical vectors ? : Getting help ?? : Getting help ^ : Vector arithmetic abline : Low-level plotting commands 92 de 99 25/02/2011 10:36 . The readline key bindings can be customized in the usual way via a ~/. As from R 2.First : Customizing the environment ..googleusercontent.12. these customizations can be conditioned on application R . Ml Change the rest of the word to lower case.inputrc file.. and “save” it. Ck Delete from cursor to end of command. Mc Change the rest of the word to upper case.Last : Customizing the environment / : Vector arithmetic : : Generating regular sequences :: : Namespaces ::: : Namespaces < : Logical vectors <<. Ct Transpose the character under the cursor with the next. The final <RET> terminates the command line editing sequence.Uma Introdução ao R http://translate. and “save” it.com/translate_c?hl=pt-BR&ie=UTF-. : Updating fitted models . Up: Top Appendix D Function and variable index ! : Logical vectors != : Logical vectors %*% : Multiplication %o% : The outer product of two arrays & : Logical vectors && : Conditional execution * : Vector arithmetic + : Vector arithmetic . Previous: The command-line editor .0. <RET> Re-submit the command to R.: Vector arithmetic . that is by including a section like $if R "\C-xd": "q('no')\n" $endif Next: Concept index . Cy Insert (yank) the last “saved” text here. Md Delete the rest of the word under the cursor.

next : Multiple graphics devices dev.prev : Multiple graphics devices dev.list : Multiple graphics devices dev.googleusercontent.frame : Making data frames density : Examining the distribution of a set of data det : Singular value decomposition and determinants detach : attach() and detach() determinant : Singular value decomposition and determinants dev.frame : Making data frames as..Uma Introdução ao R http://translate.com/translate_c?hl=pt-BR&ie=UTF-.set : Multiple graphics devices deviance : Generic functions for extracting model information diag : Multiplication dim : Arrays dotchart : Display graphics drop1 : Updating fitted models ecdf : Examining the distribution of a set of data edit : Editing data eigen : Eigenvalues and eigenvectors else : Conditional execution Error : Analysis of variance and model comparison example : Getting help 93 de 99 25/02/2011 10:36 .vector : The concatenation function c() with arrays attach : attach() and detach() attr : Getting and setting attributes attributes : Getting and setting attributes avas : Some non-standard models axis : Low-level plotting commands boxplot : One.data.off : Multiple graphics devices dev.. ace : Some non-standard models add1 : Updating fitted models anova : ANOVA tables anova : Generic functions for extracting model information aov : Analysis of variance and model comparison aperm : Generalized transpose of an array array : The array() function as.and two-sample tests break : Repetitive execution bruto : Some non-standard models C : Contrasts c : Concatenating lists c : The concatenation function c() with arrays c : Character vectors c : Vectors and assignment cbind : Forming partitioned matrices coef : Generic functions for extracting model information coefficients : Generic functions for extracting model information contour : Display graphics contrasts : Contrasts coplot : Displaying multivariate data cos : Vector arithmetic crossprod : Multiplication crossprod : Index matrices cut : Frequency tables from factors data : Accessing builtin datasets data.

exp : Vector arithmetic F : Logical vectors factor : Factors FALSE : Logical vectors fivenum : Examining the distribution of a set of data for : Repetitive execution formula : Generic functions for extracting model information function : Writing your own functions getAnywhere : Object orientation getS3method : Object orientation glm : The glm() function help : Getting help help..Uma Introdução ao R http://translate.start : Getting help hist : Display graphics hist : Examining the distribution of a set of data identify : Interacting with graphics if : Conditional execution ifelse : Conditional execution image : Display graphics is.googleusercontent.com/translate_c?hl=pt-BR&ie=UTF-.search : Getting help help.nan : Missing values jpeg : Device drivers ks..na : Missing values is.test : Examining the distribution of a set of data legend : Low-level plotting commands length : The intrinsic attributes mode and length length : Vector arithmetic levels : Factors lines : Low-level plotting commands list : Lists lm : Linear models lme : Some non-standard models locator : Interacting with graphics loess : Some non-standard models log : Vector arithmetic lqs : Some non-standard models lsfit : Least squares fitting and the QR decomposition mars : Some non-standard models max : Vector arithmetic mean : Vector arithmetic methods : Object orientation min : Vector arithmetic mode : The intrinsic attributes mode and length NA : Missing values NaN : Missing values ncol : Matrix facilities next : Repetitive execution nlm : Maximum likelihood nlm : Least squares nlm : Nonlinear least squares and maximum likelihood models nlme : Some non-standard models nlminb : Nonlinear least squares and maximum likelihood models nrow : Matrix facilities optim : Nonlinear least squares and maximum likelihood models 94 de 99 25/02/2011 10:36 .

. order : Vector arithmetic ordered : Ordered factors outer : The outer product of two arrays pairs : Displaying multivariate data par : The par() function paste : Character vectors pdf : Device drivers persp : Display graphics plot : The plot() function plot : Generic functions for extracting model information pmax : Vector arithmetic pmin : Vector arithmetic png : Device drivers points : Low-level plotting commands polygon : Low-level plotting commands postscript : Device drivers predict : Generic functions for extracting model information print : Generic functions for extracting model information prod : Vector arithmetic qqline : Display graphics qqline : Examining the distribution of a set of data qqnorm : Display graphics qqnorm : Examining the distribution of a set of data qqplot : Display graphics qr : Least squares fitting and the QR decomposition quartz : Device drivers range : Vector arithmetic rbind : Forming partitioned matrices read.googleusercontent..Uma Introdução ao R http://translate.table() function rep : Generating regular sequences repeat : Repetitive execution resid : Generic functions for extracting model information residuals : Generic functions for extracting model information rlm : Some non-standard models rm : Data permanency and removing objects scan : The scan() function sd : The function tapply() and ragged arrays search : Managing the search path seq : Generating regular sequences shapiro.table : The read.test : Examining the distribution of a set of data sin : Vector arithmetic sink : Executing commands from or diverting output to a file solve : Linear equations and inversion sort : Vector arithmetic source : Executing commands from or diverting output to a file split : Repetitive execution sqrt : Vector arithmetic stem : Examining the distribution of a set of data step : Updating fitted models step : Generic functions for extracting model information sum : Vector arithmetic summary : Generic functions for extracting model information summary : Examining the distribution of a set of data svd : Singular value decomposition and determinants 95 de 99 25/02/2011 10:36 .com/translate_c?hl=pt-BR&ie=UTF-.

googleusercontent.. Up: Top Appendix E Concept index Accessing builtin datasets : Accessing builtin datasets Additive models : Some non-standard models Analysis of variance : Analysis of variance and model comparison Arithmetic functions and operators : Vector arithmetic Arrays : Arrays Assignment : Vectors and assignment Attributes : Objects Binary operators : Defining new binary operators Box plots : One.and two-sample tests Character vectors : Character vectors Classes : Object orientation Classes : The class of an object Concatenating lists : Concatenating lists Contrasts : Contrasts Control statements : Control statements CRAN : Contributed packages and CRAN Customizing the environment : Customizing the environment Data frames : Data frames Default values : Named arguments and defaults Density estimation : Examining the distribution of a set of data Determinants : Singular value decomposition and determinants Diverting input and output : Executing commands from or diverting output to a file Dynamic graphics : Dynamic graphics Eigenvalues and eigenvectors : Eigenvalues and eigenvectors 96 de 99 25/02/2011 10:36 . Previous: Function and variable index . t : Generalized transpose of an array T : Logical vectors t.com/translate_c?hl=pt-BR&ie=UTF-.Uma Introdução ao R http://translate.and two-sample tests vcov : Generic functions for extracting model information vector : Vectors and assignment while : Repetitive execution wilcox.test : One.and two-sample tests table : Frequency tables from factors table : Index matrices tan : Vector arithmetic tapply : The function tapply() and ragged arrays text : Low-level plotting commands title : Low-level plotting commands tree : Some non-standard models TRUE : Logical vectors unclass : The class of an object update : Updating fitted models var : The function tapply() and ragged arrays var : Vector arithmetic var.test : One..test : One.and two-sample tests windows : Device drivers X11 : Device drivers | : Logical vectors || : Conditional execution ~ : Formulae for statistical models Next: References .

.googleusercontent.com/translate_c?hl=pt-BR&ie=UTF-. Empirical CDFs : Examining the distribution of a set of data Factors : Contrasts Factors : Factors Families : Families Formulae : Formulae for statistical models Generalized linear models : Generalized linear models Generalized transpose of an array : Generalized transpose of an array Generic functions : Object orientation Graphics device drivers : Device drivers Graphics parameters : The par() function Grouped expressions : Grouped expressions Indexing of and by arrays : Array indexing Indexing vectors : Index vectors Kolmogorov-Smirnov test : Examining the distribution of a set of data Least squares fitting : Least squares fitting and the QR decomposition Linear equations : Linear equations and inversion Linear models : Linear models Lists : Lists Local approximating regressions : Some non-standard models Loops and conditional execution : Loops and conditional execution Matrices : Arrays Matrix multiplication : Multiplication Maximum likelihood : Maximum likelihood Missing values : Missing values Mixed models : Some non-standard models Named arguments : Named arguments and defaults Namespace : Namespaces Nonlinear least squares : Nonlinear least squares and maximum likelihood models Object orientation : Object orientation Objects : Objects One.Uma Introdução ao R http://translate.and two-sample tests Tabulation : Frequency tables from factors Tree-based models : Some non-standard models Updating fitted models : Updating fitted models 97 de 99 25/02/2011 10:36 .and two-sample tests Ordered factors : Contrasts Ordered factors : Factors Outer products of arrays : The outer product of two arrays Packages : Packages Packages : R and statistics Probability distributions : Probability distributions QR decomposition : Least squares fitting and the QR decomposition Quantile-quantile plots : Examining the distribution of a set of data Reading data from files : Reading data from files Recycling rule : The recycling rule Recycling rule : Vector arithmetic Regular sequences : Generating regular sequences Removing objects : Data permanency and removing objects Robust regression : Some non-standard models Scope : Scope Search path : Managing the search path Shapiro-Wilk test : Examining the distribution of a set of data Singular value decomposition : Singular value decomposition and determinants Statistical models : Statistical models in R Student's t test : One.and two-sample tests : One..

. [7] Actually. John M. Up: Top Appendix F References DM Bates and DG Watts (1988).googleusercontent. Belmont. and amongst those which do some will silently discard the excess and some will use it as the start of the next line. The leading “dot” in this file name makes it invisible in normal file listings in UNIX. [4] [5] [6] of unlimited length.. Notas de Rodapé For portable R code (including that to be used in R packages) only A–Za–z0–9 should be used. John M. Second edition. CA. This is also called the “ White Book ”.. Chambers and Allan R. Chapman & Hall. New York. Chapman and Hall. Becker. Annette J. Duxbury Press. SD Silvey (1970). collapse= ss ) joins the arguments into a single character string putting ss in between... Chapman & Hall. Springer. Penguin. Statistical Inference. Vectors : Simple manipulations numbers and vectors Wilcoxon test : One. nor within the argument list of a function definition some of the consoles will not allow you to enter more. The New S Language. Wilks (1988). There are more tools for character manipulation. Chambers and Trevor J. Richard A.Last. Peter McCullagh and John A. New York. With other than vector types of argument. Dobson (1990). New York. Generalized Linear Models. John Wiley & Sons.Uma Introdução ao R http://translate. de Nova York. This is also called the “ Green Book ”. Rice (1995).value before any other statements are executed. AC Davison and DV Hinkley (1997). John A.com/translate_c?hl=pt-BR&ie=UTF-. London.and two-sample tests Workspace : Data permanency and removing objects Writing functions : Writing your own functions Previous: Concept index . See Concatenating lists . John M. Statistical Models in S. [1] [2] [3] not inside strings. the action of c() is rather different. (1992). Bootstrap Methods and Their Applications . Mathematical Statistics and Data Analysis. see the help for sub and substring . Cambridge University Press. Nonlinear Regression Analysis and Its Applications. Chambers (1998) Programming with Data . An Introduction to Generalized Linear Models . London. Chapman and Hall. This book is often called the “ Blue Book ”. London. Hastie eds. Second edition. [ 8 ] paste(. 25/02/2011 10:36 98 de 99 . such as list mode arguments. Nelder (1989). it is still available as .

A different style using `formal' or `S4' classes is provided in package methods . as explained in the manual. Queensland. namely integer and double precision. eg. [ 23 ] [ 24 ] 2. or use xyplot from package lattice . South Australia. [ 10 ] [ 11 ] In general. 3.factor() ). because of roundoff errors in the character representation. to be discussed later. The matrix xx' may be calculated either by cbind(x) %*% x or x %*% rbind(x) since the result of rbind() or cbind() is always a matrix. perhaps using the Cholesky or eigendecomposition of A. Some graphics parameters such as the size of the current device are for information only. In such cases the smaller matrix seems implicitly to be the interpretation adopted. [9] numeric mode is actually an amalgam of two distinct modes. [ 15 ] Note that x %*% x is ambiguous.R-project.. eg..googleusercontent. [ 25 ] [ 26 ] 99 de 99 25/02/2011 10:36 . coercion from numeric to character and back again will not be exactly reversible. Note however that length( object ) does not always contain intrinsic useful information. namely the Australian Capital Territory. However. [ 16 ] [ 17 ] [ 18 ] [ 19 ] [ 20 ] [ 21 ] See the on-line help for autoload for the meaning of the second term. since arguments are coerced to factors when necessary (using as. as it could mean either x'x or x x'. the utilities Sed or Awk can be used.com/translate_c?hl=pt-BR&ie=UTF-. Even better would be to form a matrix square root B with A = BB' and find the squared length of the solution of By = x.5Gb on some 64-bit versions of Windows. [ 14 ] Note that tapply() also works in this case when its second argument is not a factor.9.org On a PC keyboard this is usually the Alt key.5Gb on versions of Windows that support 3Gb per process and have the support enabled: see the rw-FAQ Q2. where x is the column form. the Northern Territory. the best way to compute x'x or xx' is crossprod(x) or x %o% x respectively. Victoria and Western Australia. See also the methods described in Statistical models in R In some sense this mimics the behavior in S-PLUS since in S-P LUS this operator always creates or assigns to a global variable. see the URL http://ESS. Tasmania. occasionally the `Windows' key. New South Wales. ' tapply(incomes. state) '. Under UNIX. [ 22 ] So it is hidden under UNIX. [ 12 ] [ 13 ] Readers should note that there are eight states and territories in Australia.Uma Introdução ao R http://translate. when object is a function. and this is true for quite a few other functions. The `Emacs Speaks Statistics' package. so the scalar x'x is in this case the result.