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

e ampliou alguns dos materiais. Sugestões para o leitor A maioria dos novatos R começará com a sessão introdutória no Apêndice A.org . Por favor. endereço para correspondência e-mail para R-core@R-project.Uma Introdução ao R http://translate. Anterior: Prefácio . 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. Isto deve dar alguma familiaridade com o estilo de R sessões e mais importante feedback algum instante sobre o que realmente acontece. Muitos usuários chegará a R principalmente para as suas instalações gráficas.. desta forma. Anterior: Top . Neste caso. Comentários e correções são sempre bem vindos.. 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 . Introdução e preliminares Seguinte: manipulações simples números e vetores . Gostaríamos de agradecer sinceramente a Bill Venables (e David Smith) para a concessão de permissão para distribuir esta versão modificada das notas. Smith quando da Universidade de Adelaide. Up: Top 1 Introdução e preliminares 4 de 99 25/02/2011 10:36 .googleusercontent. e por ser um defensor da R do caminho de volta. Fizemos uma série de pequenas alterações para refletir as diferenças entre os programas R e S.com/translate_c?hl=pt-BR&ie=UTF-. 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

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

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

6 10 de 99 25/02/2011 10:36 . 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. Ao mesmo tempo. Nomes como este são muitas vezes significativos no contexto de uma única análise. bar) Todos os objetos criados durante uma sessão de R pode ser armazenado permanentemente em um arquivo para uso em futuras sessões R.7.Uma Introdução ao R http://translate.4 e 21. mas pode ser bastante difícil decidir o que pode ser quando as análises foram conduzidas várias no mesmo diretório. 10. y. 6. Se você indicar que você quer fazer isso. ou seja. foo.com/translate_c?hl=pt-BR&ie=UTF-. A estrutura mais simples como é o vetor numérico.6. Up: Top Duas manipulações simples.. z. Quando R é iniciado na tarde do mesmo diretório que recarrega o espaço de trabalho a partir deste arquivo. digamos. que consiste em uma coleção ordenada de números. Recomenda-se que você deve usar separar diretórios de trabalho para as análises efectuadas com R.7) Esta é uma declaração de atribuição usando a função c() que. ls() ) pode ser usado para exibir os nomes dos (a maioria) os objetos que estão atualmente armazenados no R.c (10. 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 . 5. use o comando R > X <. O comando R objetos> () (Alternativamente. Anterior: Introdução e preliminares . partir de tais componentes. temp. o associado do histórico dos comandos é recarregada. e as linhas de comando usado na sessão são salvos em um arquivo chamado. 5. os objetos são gravados em um arquivo chamado. 21. 3. A coleção de objetos armazenados atualmente é chamado o espaço de trabalho.6. consistindo de cinco números. 6.1 Vetores e atribuição R opera sobre estruturas de dados nomeado.1. Rdata 5 no diretório atual. Durante uma sessão I.4. 3. Seguinte: Objetos . Up: Simple números manipulações e vetores 2. Para remover objetos da função rm está disponível: > Rm (x.googleusercontent. Rhistory. anterior: Simple números manipulações e vetores . os objetos são criados e armazenados pelo nome (discutiremos esse processo na próxima sessão)..4. que é uma entidade única. No final de cada sessão R é-lhe dada a oportunidade de salvar todos os objetos disponíveis no momento. tinta. sucata. É bastante comum para objetos com nomes x e y a ser criado durante a análise. Para configurar um vetor denominado x .1.4.

sin . e 1 repetido 11 vezes.7)) O operador de costume. c(min(x). uma constante é simplesmente repetido.6. tan . com as atribuições acima do comando V <> . o valor é impresso e perdeu 7 .4. e assim por diante. <. respectivamente. c (10.Uma Introdução ao R http://translate. sqrt . Em especial. Atribuição também pode ser feita usando a função assign() . 5.1. é claro.. 0. vetores mais curtos na expressão são recicladas quantas vezes necessário (talvez fracionada). que ocorre na expressão.4. até que elas coincidam com o comprimento do maior vetor. Além de todas as funções aritméticas comuns estão disponíveis. Seguinte: regular gerar seqüências . o valor da expressão é um vetor com o mesmo comprimento que o maior vetor. x) criaria um vetor y com 11 entradas composto de duas cópias de x com um zero no lugar do meio. Observe que o operador de atribuição (' <. log . Na maioria dos contextos. Up: Simple números manipulações e vetores 2. pode ser pensado como um sintática atalho para isso. a ' = operador pode ser usado como uma alternativa. e var(x) que dá sum ((x-média (x)) ^ 2) / (comprimento (x) -1) 11 de 99 25/02/2011 10:36 . range é uma função cujo valor é um vetor de comprimento dois. agora. a mesma atribuição pode ser feita usando > C (10. Se não forem. / e ^ para elevar a uma potência. Uma maneira equivalente de fazer a mesma tarefa como acima está com: > Assign ("x". se tivéssemos que usar o comando > 1 / x os inversos dos cinco valores seriam impressas no terminal (eo valor de x . Um número que ocorre por si só. exp . Assim. permanece inalterado). Então. em uma expressão é tida como um vetor de comprimento um. 3.2 aritmética Vector Vetores podem ser usados em expressões aritméticas.. 6. elemento por elemento."(" menos ") que ocorrem estritamente lado a lado e` pontos 'para o objeto que recebe o valor da expressão.2 * x + y + 1 gera um novo vetor v de comprimento 11 construído pela soma.com/translate_c?hl=pt-BR&ie=UTF-. Atribuições também pode ser feita em outra direção.1. Vetores ocorrendo na mesma expressão não precisam ser todos do mesmo comprimento. usando a evidente mudança de operador de atribuição. Assim. que consiste de dois personagens do < "(" menor que ") e" . que é a mesma sum(x)/length(x) .googleusercontent. A tarefa ainda mais <> Y . 3. isto é. 2*x 2. 21. Os operadores aritméticos elementares são os habituais + . caso em que as operações são realizadas elemento por elemento. sum(x) dá o total dos elementos em x .. todos têm seu significado usual. * .c (x. 6. Precedente: Vetores e atribuição .'). max e min e selecionar o menor eo maior elementos de um vetor.4.. 5. max(x)) . 21.2 repetidas vezes.4. . Duas funções estatísticas são mean(x) que calcula a média da amostra. cos .7) -> x Se uma expressão é usada como um comando completo. length(x) é o número de elementos em x . e prod(x) o seu produto. y repetida apenas uma vez.6.

5. Assim sqrt (-17) dará NaN e uma advertência. Note-se que max e min e selecionar o menor eo maior valores em seus argumentos.10 e comparar as seqüências 1:n-1 e 1:(n-1) . 2.Uma Introdução ao R http://translate. retorna um vetor do mesmo tamanho de x com os elementos dispostos em ordem crescente. seq(from=1. Os primeiros dois parâmetros pode ser chamado from= valor e to= valor.3 seqüências regulares R tem um número de instalações para a geração de seqüências comumente utilizado de números. também pode ser dada em forma de nome.30) .. por exemplo 2*1:15 é o vetor c(2. porém existem outras instalações de classificação mais flexível disponível (veja a order() ou sort. Up: manipulações simples números e vetores Geração de 2. ou variância da amostra. regular gerar seqüências Seguinte: vetores lógicos . que especifica um tamanho de passo e um comprimento para a seqüência respectivamente.6. 4.. 5.list() que produzem uma permutação para fazer a classificação) .. A construção 30:1 pode ser usado para gerar uma seqüência para trás. assim seq(1. -4.0) . por isso. .. from=1) são todos iguais como 1:30 .. O operador dois pontos tem alta prioridade dentro de uma expressão.10) é o mesmo vetor como 2:10 . 4. 30) . A função seq() é um mecanismo mais geral para a geração de seqüências.. o padrão by=1 é assumido. mas sqrt (-17 0 i) fará os cálculos de números complexos. sort(x) Para trabalhar com números complexos. Para a maioria dos efeitos que o usuário não se preocupa se os "números" em um vetor numérico são inteiros. Os próximos dois parâmetros para seq() pode ser chamado by= valor e length= valor. Por exemplo > Seq (-5. -4. mesmo se eles tiverem vários vetores. Se nenhum desses for dada. e para muitas funções R outro.. os cálculos são feitos com precisão dupla números reais ou números de precisão dupla complexo se os dados de entrada são complexas. se houver.com/translate_c?hl=pt-BR&ie=UTF-. Ela tem cinco argumentos. 2) -> s3 gera em s3 o vetor c(-5.. e se estes são os dois únicos argumentos que apresenta o resultado é o mesmo que o operador dois pontos. reais ou mesmo complexos. . Do mesmo modo 12 de 99 25/02/2011 10:36 . fonte de uma parte explícita complexo.. 29.8.0. Coloque n <.6.8.. caso em que a ordem em que aparecem é irrelevante. 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. por =. 28. Internamente. 4.. 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.googleusercontent. . to=30) e seq(to=30. Os primeiros dois argumentos. Parâmetros para seq() . só algumas das quais podem ser especificados em qualquer uma chamada. especificar o início eo fim da seqüência. Isso é seq(2. Por exemplo 1:30 é o vetor c(1. Precedente: aritmética Vector . 30) .

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

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

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. Um vetor lógico. Também > (X +1) [(! Is.c (5. nessa ordem. 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. length(x) }. Seguinte: Outros tipos de objetos . Por exemplo. "y". Mais geral. y será menor que x . Esse índice vetor uma especifica os valores a serem excluídos e não incluídos. 3. vetores Esse índice pode ser qualquer um dos quatro tipos distintos. Neste caso. mas os cinco primeiros elementos de x . "y".na (x)] cria (ou recria) um objeto y que conterá os valores em falta.7 vetores. na mesma ordem do. "banana".. o índice do vetor deve ser do mesmo comprimento que o vetor a partir da qual os elementos devem ser selecionados. O vetor de índice pode ser de qualquer tamanho. um sub-vetor do vetor de nomes podem ser utilizados da mesma forma como os rótulos positivos integral no item 2 mais acima.1).Uma Introdução ao R http://translate.[c ("maçã".2. anterior: Personagem vetores . "y") [rep (c (1.. 2. "x" repetido quatro vezes. Note que se x tem valores em falta. eo resultado é do mesmo comprimento que o vetor de índice. . "laranja")] frutas 15 de 99 25/02/2011 10:36 . Um vetor de seqüências de caracteres. Neste caso. Por exemplo <> Y .com/translate_c?hl=pt-BR&ie=UTF-. 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)..c ("laranja". não de x . Um vetor de quantidades negativas integral. "maçã". 2. Um vetor de quantidades positivas integral. Esta possibilidade só se aplica quando um objeto tem um names de atributo para identificar seus componentes. 1. no resultado.x [. 4. Assim <> Y . Os elementos correspondentes do vetor são selecionadas e concatenadas.(1:5)] dá y todos. Neste caso.googleusercontent. 10.x [! Is. Também > C ("x".. 20) > Nomes (fruta) <. os valores no vetor de índice deve estar no conjunto {1. 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. 1.2. os tempos = 4)] (Uma coisa improvável certo a fazer) produz um vetor de caracteres de tamanho 16 que consiste em "x". Up: manipulações simples números e vetores Índice de 2. Valores correspondentes a TRUE no vetor de índice são selecionados e os correspondentes à FALSE são omitidos. "pêssego") > <Almoço .. <> Fruta .

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

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

que são neste momento os dois NA ). por exemplo. 18 de 99 25/02/2011 10:36 .10) R permite tratar z . simplesmente.googleusercontent. foi criado. A função attr( objeto . é claro. dando-lhe um valor de índice fora do intervalo anterior. Do mesmo modo character() é um vetor de caracteres vazia. Seguinte: A classe de um objeto . no scan() função para a entrada. (Veja o scan () função . como se fosse um-por-10 da matriz 10. Depois que um objeto de qualquer tamanho. por exemplo. se alpha é um objeto de comprimento 10. 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. para associar a criação de uma data ou um operador com um objeto R. da mesma forma. Portanto. Alguns cuidados devem ser tomados quando atribuir ou excluir atributos pois eles são uma parte integrante do sistema de objetos usados em R. Isso se aplica a qualquer estrutura de todos.c (10.2 Alterando o comprimento de um objeto Um objeto "vazio" pode ainda ter um modo.numérico () faz e uma estrutura de vetor vazio de modo numérico.3 e vetores pode ser estendido (por valores em falta). Anterior: Mudando o comprimento de um objeto . (os dois primeiros componentes. novos componentes podem ser adicionados a ele. exceto em circunstâncias muito especial quando algum novo atributo está sendo criado para algum propósito particular. O conceito. Up: Objetos 3. > <. Seguinte: Como obter e definir atributos .Uma Introdução ao R http://translate. Por exemplo > Attr (z. desde o modo do componente adicional (s) concorda com o modo do objeto em primeiro lugar.17 faz agora e um vetor de comprimento 3. mesmo com o índice.. (Os índices de idade não são mantidas. é muito importante. > Comprimento (alfa) <.Alfa alfa [2 * 01:05] torna um objeto de comprimento 5 que compreende apenas os componentes antigos. nome ) pode ser usado para selecionar um atributo específico. Essas funções são raramente utilizadas.. Assim > E [3] <.) Podemos então manter apenas os três primeiros valores.) Inversamente para truncar o tamanho de um objeto requer apenas uma atribuição para fazê-lo. Por exemplo > E <. e assim por diante. Up: Objetos 3. Anterior: O modo de atributos intrínsecos e comprimento . entretanto.3 obter e definir atributos A função de attributes( objeto ) retorna uma lista de todos os não-atributos intrínsecos atualmente definidas para esse objeto.com/translate_c?hl=pt-BR&ie=UTF-. "dim") <. Este ajuste automático do comprimento de um objeto é usado com freqüência.

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

O resultado é uma estrutura do mesmo comprimento que os níveis de atributo do elemento que contém os resultados. Para isso. como se fossem as estruturas do vetor separados . aqui statef 14 .500 53. e neste caso era desnecessária.5 5.2 A função tapply() e matrizes irregulares Para continuar o exemplo anterior.500 56. 49. 52. em escrever suas próprias funções . 58. Suponha ainda que precisávamos para calcular o desvio padrão da renda do estado significa. 43) Para calcular a média da amostra de renda para cada estado agora podemos usar a função especial tapply() : > Incmeans <. indicada pelo serviço: > <Stderr .Tapply (rendas. visto que R tem também uma função embutida sd() ). suponha que temos os rendimentos dos auditores fiscais num outro vector (em unidades suficientemente grande de dinheiro) <> Renda .. tal função é muito simples de uma linha.Uma Introdução ao R http://translate. 48. "nsw" nt "qld" sa "" tas "vic" wa " O Tapply função () e matrizes irregulares fatores ordenada Seguinte: fatores ordenada .244 2. 41. O leitor deve consultar o documento de ajuda para mais detalhes.1061 2. statef. 49. 48.. 56.function (x) sqrt (var (x) / comprimento (x)) (Funções de escrita será considerada mais tarde. 42. 58. Up: Fatores 4.com/translate_c?hl=pt-BR&ie=UTF-.000 52. aqui mean() . 46. Depois desta atribuição. 62. 61. aqui incomes . 59. definidos pelos níveis do segundo componente.5 4. 70. > Níveis (statef) [1] "acto".c (60.7386 0. 61. statef stderr) e os valores calculados são então incster> ato sa nt nsw qld tas wa vic 1.600 55. 59. 51. Precedente: Fatores . 64. 61.333 55.000 60. 46.500 57. 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.6575 20 de 99 25/02/2011 10:36 . Como não há uma função embutida var() para calcular a variância da amostra.3102 4. 60. 54. precisamos escrever uma função de R para calcular o erro padrão para qualquer vector dado.250 A função tapply() é usada para aplicar uma função. 40. 49. 61.Tapply (rendas. 65. média) dando um vetor de meios com os componentes marcados pelos níveis ato sa nt nsw qld tas wa vic 44. 69. os erros-padrão são calculados por <Incster> .5 4.googleusercontent. para cada grupo de componentes do primeiro argumento.

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

. Up: matrizes e matrizes 5.1. é c(3. Matrizes podem ser unidimensionais: matrizes deste tipo são normalmente tratados da mesma forma como vetores (incluindo a imprimir).1]. digamos Z . Além disso. se o único índice não é um vetor. que é o mesmo que omitir a totalmente subscritos e usar a só.2) . a [2. mas as exceções podem causar confusão. então há 3 * 4 * 2 = 24 entradas em a vetor de dados e os mantém na ordem a[1. em seguida.100) lhe confere o atributo dim que permite que ele seja tratado como um "3 by 5 por 100 matriz. a[2. diz a . Seguinte: Índice de matrizes . a[. a[2.4. no entanto. tais como matrix() e array() estão disponíveis para simples e mais natural atribuições de quem. uma matriz é um array de 2 dimensões. a [2. Este não é o caso.1]. se um nome de matriz é dado com apenas um índice ou um vetor de índice. mas também uma matriz. como veremos em A matriz () função . Mais genericamente. dando uma seqüência de vetores de índice.. a [2.2]. a[2.4.2.1. z é um vetor de 1500 elementos. que é "grande encomenda de coluna". no entanto.1.1]. a [2.2 a indexação de matriz. Continuando o exemplo anterior. um [2.2] . por exemplo. anterior: a indexação de matriz . se qualquer posição do índice é dado um vetor de índice de vazios. se o vetor de dimensão para uma matriz. como estamos proximos discutir..1]. matriz é k-dimensional.4..2]. Subseções de uma matriz Os elementos individuais de uma matriz pode ser referenciado por dar o nome da matriz seguido pelos subscritos entre colchetes. a [2.com/translate_c?hl=pt-BR&ie=UTF-.] representa a matriz inteira.c (3. a [2. os valores correspondentes do vetor de dados só são utilizadas. Índice de matrizes A função Array () Seguinte: A função Array () .1]. Por exemplo. o vetor de dimensão pode ser referenciado explicitamente como dim(Z) (em ambos os lados de uma atribuição). toda a gama de subscrição que for tomada. com o primeiro subscrito mais rápidos e mais lentos subscrito passado. neste caso o vetor de dimensão é ignorada.2. a[3. Um vetor pode ser usado por R como uma matriz somente se ele tiver um vetor de dimensão como o seu atributo dim. por exemplo. Anterior: Matrizes . .2].1..Uma Introdução ao R http://translate.2) eo vetor de dados contendo os valores c (a [2. separados por vírgulas..2]. Os valores no vetor de dados fornecem os valores da matriz na mesma ordem em que iria ocorrer em Fortran.1]. as subseções de uma matriz pode ser especificado. Up: matrizes e matrizes 22 de 99 25/02/2011 10:36 . em seguida.googleusercontent.3. Para qualquer matriz.. Suponha.] é um 4 * 2 matriz com a dimensão do vetor c(4.4.5.2]) nessa ordem.4. As dimensões são indexados a partir de um até os valores indicados no vetor de dimensão. em substituição de índices. A atribuição > Dim (z) <.3. Outras funções.

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

com/translate_c?hl=pt-BR&ie=UTF-. que tem a forma > Z <. e isso se torna o vetor de dimensão do resultado. se o vetor h tem 24 ou menos. Se o tamanho h é exatamente 24. então > D <. se A .2)) usaria h criar 3 por 4 a 2 na série Z . os seus valores são reciclados a partir do início de novo para fazê-lo até o tamanho 24 (ver A regra da reciclagem ). Anterior: Índice de matrizes . c (3.4..2) e Z[1:24] representa o vetor de dados como era no h .c (3. Como um exemplo extremo. Portanto. dim (Z) <.googleusercontent. > N <.array (0. um caráter lógico ou matriz) fornecidos como uma matriz é tratada como um vetor de indexação. se h for menor que 24.4.Uma Introdução ao R http://translate.2) seria um sinal de erro sobre o descasamento comprimento.matriz (h. Da experiência que temos encontrado o seguinte para ser um guia confiável. A regra da reciclagem Precedente: matriz A () função . o resultado é o mesmo que > Z <. variedades) Índice de matrizes deve ser numérica: qualquer outra forma de matriz (por exemplo.1 vetores e aritmética mista matriz. Up: matriz A () função 5. mas dim(h) <. dim_vector) Por exemplo.4. Matrizes podem ser usadas em expressões aritméticas eo resultado é um conjunto formado por operações elemento por elemento do vetor de dados. dim(Z) representa o vetor de dimensão c(3.h.matriz (data_vector. mas comuns > Z <. No entanto.2) No entanto.4.c(3. B e C são matrizes semelhantes.2)) torna Z uma matriz de zeros. Qualquer operandos vetoriais curto são estendidos através da reciclagem de seus valores 24 de 99 25/02/2011 10:36 .tabela (blocos. Seguinte: O produto externo das duas matrizes .. então o comando > Z <.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. 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. O dim atributos de operandos geralmente precisa ser o mesmo. c = dim (3.4. Neste ponto. e Z[] com um índice vazio ou Z com não subscrito representa a matriz inteira como uma matriz. a regra precisa quanto à matriz mista e os cálculos do vetor tem que ser considerado um pouco mais de cuidado. A expressão é digitalizado a partir da esquerda para a direita. os números.4 O array() função Bem como dar uma estrutura de um vetor dim atributo. Up: matrizes e matrizes 5.4. os vetores podem ser construídos a partir de vetores da array função.

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

. Up: matrizes e matrizes 5. Precedente: Generalized transposição de uma matriz .aperm (A. é um caso tão importante e específico que necessita de uma discussão em separado.. os vetores que ocorrem em expressões de multiplicação de matrizes são automaticamente promovidos tanto aos vetores linha ou coluna. como vemos mais tarde). então B dada por > B <. Seguinte: Formação matrizes particionadas . a . (embora nem sempre isso é possível de forma inequívoca. O argumento perm deve ser uma permutação dos inteiros {1..7.1)) é apenas a transposição de A .. As funções nrow(A) e ncol(A) indicar o número de linhas e colunas na matriz A . Up: instalações Matrix 5. R contém muitos operadores e funções que estão disponíveis apenas para as matrizes. Um n por 1 ou por uma matriz n pode.Uma Introdução ao R http://translate.. O resultado da função é uma matriz do mesmo tamanho que a velho. k}.6 transposição generalizada de uma matriz A função aperm(a. ser usado como um vetor n-se no contexto como é apropriado. onde k é o número de subscritos em a . se A é uma matriz (ou seja. Se.googleusercontent. No entanto.7 instalações Matrix Como mencionado acima. perm) pode ser usado para permutar uma matriz.. Também é surpreendente que cerca de 1 em 20 matrizes seja singular.com/translate_c?hl=pt-BR&ie=UTF-. t(X) é a função de transpor a matriz. é tão ineficaz quanto a ser impraticável. então poderíamos ter usado B <. para ser discutido em Loops e execução condicional . Para este caso específico uma simples função de t() está disponível. Up: matrizes e matrizes 5. A maneira mais fácil pensar desta operação é como uma generalização da transposição para as matrizes. Por exemplo. A e B são matrizes quadradas do mesmo tamanho. naturalmente.1 A multiplicação de matrizes O operador %*% é usado para multiplicação de matrizes. Por outro lado. uma subscrita matriz duplamente).t(A) . então > A * B é a matriz de elemento por elemento e produtos > A *%% B 26 de 99 25/02/2011 10:36 . se possível. 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 . como descrito acima. por exemplo. De fato. o que for multiplicatively coerente. Seguinte: instalações Matrix . Precedente: O exterior do produto de duas matrizes . Precedente: instalações Matriz . respectivamente. C (2. uma matriz é apenas uma matriz com dois subscritos. mas com dimensão dada por perm[j] se tornando o novo j ª dimensão.

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

See the help facility for more details. O resultado da svd(M) é na verdade uma lista de três componentes chamados d .4 decomposição em valores singulares e determinantes A função svd(M) tem uma matriz de argumentos arbitrários. and another.googleusercontent. u e v .values = TRUE) $ valores Seguinte: Mínimos quadrados montagem ea decomposição QR . to calculate the trace of a square matrix. including the sign. As a further trivial but potentially useful example. Se a expressão > Eigen (Sm) é usado por si só como um comando os dois componentes são impressas. Up: Matrix facilities 5. com significados evidentes.Uma Introdução ao R http://translate. Up: instalações Matrix 5. evals agora detém o vetor de autovalores eo segundo componente é descartado. to give the sign and modulus (optionally on log scale).qr(X) > b <. 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) .7. com os seus nomes. among other things. Another closely related function is qr() and its allies.coef(Xplus.prod (svd (M) $ d) calcula o valor absoluto do determinante de M . An assignment such as > ans <. regression diagnostics. Se M é na praça de fato.função (M) prod (svd (M) $ d) after which we could use absdet() as just another R function.com/translate_c?hl=pt-BR&ie=UTF-. não é difícil perceber que > AbsdetM <. say tr() . [Hint: You will not need to use an explicit loop.7.5 Least squares fitting and the QR decomposition The function lsfit() returns a list giving results of a least squares fitting procedure. determinant . Further note that you almost always will prefer using lm(. D é realmente voltou como um vetor de elementos da diagonal. you might like to consider writing a function. Look again at the diag() function. muitas vezes com uma variedade de matrizes pode ser definida como uma função de R > <Absdet .. Note that a grand mean term is automatically included and need not be included explicitly as a column of X .) (see Linear models ) to lsfit() for regression modelling. segundo uma matriz de colunas ortonormais V . y) gives the results of a least squares fit where y is the vector of observations and X is the design matrix. Se este cálculo fosse necessário. M . Consider the following assignments > Xplus <.lsfit(X. y) 28 de 99 25/02/2011 10:36 .diag() for.eigen (Sm.. Previous: Singular value decomposition and determinants . and also for the follow-up function ls.qr. e calcula a decomposição em valores singulares de M . então. Para grandes matrizes é melhor evitar a computação autovetores se eles não são necessários ao usar a expressão evals> <. Precedente: Autovalores e autovetores . Este consiste de uma matriz de colunas ortonormais U com o espaço mesma coluna M . only.] R has a builtin function det to calculate a determinant.

. possibly cyclically extended. X2) The result of rbind() or cbind() always has matrix status.resid(Xplus.) the arguments to cbind() must be either vectors of any length.. Redundancies will be discovered and removed as they are found. Up: Arrays and matrices 5. and rbind() vertically. y) > res <. > fit <. or matrices with the same column size. The result is a matrix with the concatenated arguments arg_1 . . are of course taken as row vectors. or row-wise. low-level way to perform least squares calculations.. .fitted(Xplus. but rather clears numeric objects of all dim and dimnames attributes. Although still useful in some contexts..vector() 29 de 99 25/02/2011 10:36 . X1. Next: The concatenation function c() with arrays .Uma Introdução ao R http://translate. that is the same number of rows. 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. or column-wise. that is.cbind(1. Previous: Matrix facilities . Previous: Forming partitioned matrices . c() . arg_2 . cbind() and rbind() As we have already seen informally. with arrays It should be noted that whereas cbind() and rbind() are concatenation functions that respect dim attributes. Up: Arrays and matrices 5. the projection onto the orthogonal complement in res and the coefficient vector for the projection in b . If some of the arguments to cbind() are vectors they may be shorter than the column size of any matrices present. This alternative is the older. it would now generally be replaced by the statistical models features. the basic c() function does not.. arg_3 . Suppose X1 and X2 have the same number of rows. b is essentially the result of the MATLAB `backslash' operator.googleusercontent. The function rbind() does the corresponding operation for rows..8 Forming partitioned matrices.9 The concatenation function. To combine these by columns into a matrix X . as will be discussed in Statistical models in R . together with an initial column of 1 s we can use > X <. arg_2 .qr. y) These compute the orthogonal projection of y onto the range of X in fit .cbind( arg_1 . In this case any vector argument. Next: Frequency tables from factors . 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). The official way to coerce an array back to a simple vector object is to use as. matrices can be built up from other vectors and matrices by the functions cbind() and rbind() .qr. This is occasionally useful in its own right. forming the columns.com/translate_c?hl=pt-BR&ie=UTF-. In the assignment > X <. It is not assumed that X has full column rank. Roughly cbind() forms matrices by binding together matrices horizontally.

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

If it is a named list.googleusercontent.. Here is a simple example of how to make a list: > Lst <. Up: Lists and data frames 31 de 99 25/02/2011 10:36 ."name". There is no particular need for the components to be of the same mode or type. of course.children=3. Lst[["name"]] is the same as Lst$name .7. Lst[[x]] It is very important to distinguish Lst[[1]] from Lst[1] . similarly be given a names attribute also. the names are transferred to the sublist.. wife="Mary". Thus Lst$coefficients may be minimally specified as Lst$coe and Lst$covariance as Lst$cov . one can also use the names of the list components in double square brackets. a matrix. for example.Uma Introdução ao R http://translate. a complex vector.. a logical value. ] ' is a general subscripting operator. If Lst is a list. Thus if Lst is the name of a list with four components. Lst[[2]] .. Thus the former is the first object in the list Lst .1 Lists An R list is an object consisting of an ordered collection of objects known as its components . Next: Data frames .ages=c(4. ' [[ . and so on. The latter is a sublist of the list Lst consisting of the first entry only. by giving an expression of the form > name $ component_name for the same thing.. a list could consist of a numeric vector. no. ie. ]] ' is the operator used to select a single element. whereas ' [ . and. when the name of the component to be extracted is stored in another variable as in > x <. Lst[[4]] is a vector subscripted array then Lst[[4]][1] is its first entry. The vector of names is in fact simply an attribute of the list like any other and may be handled as such. further. The names of components may be abbreviated down to the minimum number of letters needed to identify them uniquely. is the same as Lst[[2]] and is the string "Mary" . 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. Other structures besides lists may.ages[1] Additionally.com/translate_c?hl=pt-BR&ie=UTF-. then the function length(Lst) gives the number of (top level) components it has. So in the simple example given above: Lst$name Lst$wife is the same as Lst[[1]] and is the string "Fred" . and if it is a named list the name is not included.list(name="Fred". If. Lst$child. these may be individually referred to as Lst[[1]] . This is a very useful convention as it makes it easier to get the right component if you forget the number. Components of lists may also be named . more conveniently. a function. is the same as Lst[[4]][1] and is the number 4 . child. 6. Lst[[3]] and Lst[[4]] . This is especially useful. Previous: Lists .. a character array. or.9)) Components are always numbered and may always be referred to as such.

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. logicals and factors are included as is.list(matrix=Mat) Concatenating lists Previous: Constructing and modifying lists . It may be displayed in matrix form. and matrix structures must all have the same row size . Numeric vectors. . or variables. 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. object_m for the components and giving them names as specified by the argument names. factors. character. Matrices. and data frames provide as many variables to the new data frame as they have columns. lists. > list. the components are numbered only. numeric matrices.1 Concatenating lists When the concatenation function c() is given list arguments.2 Constructing and modifying lists New lists may be formed from existing objects by the function list() . whose levels are the unique values appearing in the vector.C) Recall that with vector objects as arguments the concatenation function similarly joined together all arguments into a single vector structure. If these names are omitted. Vector structures appearing as variables of the data frame must all have the same length . Up: Constructing and modifying lists 6. Lists.. lists. An assignment of the form > Lst <.A. 6. In this case all other attributes. and character vectors are coerced to be factors. Previous: Constructing and modifying lists .frame" .ABC <. list. can be extended by specifying additional components.list( name_1 = object_1 .. elements. . name_m = object_m ) sets up a list Lst of m components using object_1 .3 Data frames A data frame is a list with class "data. such as dim attributes.B..Uma Introdução ao R http://translate.com/translate_c?hl=pt-BR&ie=UTF-.c(list. or other data frames. . whose components are those of the argument lists joined together in sequence. respectively. A data frame may for many purposes be regarded as a matrix with columns possibly of differing modes and attributes. the result is an object of mode list also. like any subscripted object.. Por exemplo > Lst[5] <. (which can be freely chosen).2. list. Up: Lists and data frames 6...googleusercontent. There are restrictions on lists that may be made into data frames. are discarded. or logical).

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

we detach the data frame and confirm it has been removed from the search path. by position number or.GlobalEnv is the workspace. for example. add any variables you wish to keep for future reference to the data frame using the $ form of assignment. > detach("lentils") 34 de 99 25/02/2011 10:36 .list) Anything that has been attached can be detached by detach . and then detach() . Initially it gives > search() [1] ".GlobalEnv" "Autoloads" "package:base" where . Next: Managing the search path . all of which have variables named x . and use the working directory at level 1 for operational quantities and temporary variables. In particular any object of mode "list" may be attached in the same way: attach() > attach(any.com/translate_c?hl=pt-BR&ie=UTF-. by name. but other classes of object as well.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. finally remove all unwanted variables from the working directory and keep it as clean of left-over temporary variables as possible.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.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.. Previous: Attaching arbitrary lists .3. Previous: Working with data frames .3.old.. Next: Attaching arbitrary lists . preferably.googleusercontent.3. before leaving a problem. y and z . Previous: attach() and detach() . Up: Data frames 6. Finally. when working with a problem attach the appropriate data frame at position 2 . Up: Data frames 6. In this way it is quite simple to work with many problems in the same directory.Uma Introdução ao R http://translate. Up: Data frames 6.4 Attaching arbitrary lists is a generic function that allows not only directories and data frames to be attached to the search path. 17 After lentils is attached we have > search() [1] ".

com/translate_c?hl=pt-BR&ie=UTF-. R input facilities are simple and their requirements are fairly strict and even rather inflexible.75 93..5 no 03 57.data") Often you will want to omit including the row labels directly and use the default labels. There is a clear presumption by the designers of R that you will be able to modify your input files using other tools.0 710 5 7. For more details on importing data into R and also exporting data. Up: Reading data from files 7. By default numeric items (except row labels) are read as numeric variables and non-numeric variables. Previous: Reading data from files .Uma Introdução ao R http://translate.. If the file has one fewer item in its first line than in its second.50 101.0 830 5 6.table("houses. see the R Data Import/Export manual.table() function. scan() . 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. the external file will normally have a special form. The function read.00 111.heat in the example.9 yes . this arrangement is presumed to be in force. Previous: Lists and data frames . In this 35 de 99 25/02/2011 10:36 . an entire data frame can be read directly with the read.googleusercontent.table() can then be used to read the data frame directly > HousePrice <. Each additional line of the file has as its first item a row label and the values for each variable.50 131.. as factors.0 1000 5 4. So the first few lines of a file to be read as a data frame might look as follows.table() function To read an entire data frame directly. that can be called directly. If variables are to be held mainly in data frames.0 900 5 1. Generally this is very simple. There is also a more primitive input function.read.GlobalEnv" "Autoloads" "package:base" Next: Probability distributions .heat 01 52.table() function The scan() function Accessing builtin datasets Editing data Next: The scan() function . such as Cent. This can be changed if necessary.75 128. The read.0 690 6 8. as we strongly suggest they should be. such as file editors or Perl 18 to fit in with the requirements of R..1 The read.8 no 05 59.2 no 04 57. Input file form with names and row labels: Price Floor Area Rooms Age Cent.2 no 02 54. > search() [1] ". The first line of the file should have a name for each variable in the data frame.

inp[[1]]. 0). Floor Area Rooms Age Cent.heat 111. a single vector is read in.. Further suppose that there are three vectors.9 yes The data frame may then be read as > HousePrice <.2 The scan() function Suppose the data vectors are of equal length and are to be read in parallel.75 . x=0.data". x <.table("houses. The result..0 830 5 6.0)) The second argument is a dummy list structure that establishes the mode of the three vectors to be read.0 900 5 1.0 690 6 8.0. If the second argument is a single value and not a list. in which case the names can be used to access the vectors read in.8 no 93.2 no 128.dat". by implication from the form of the file. > X <.dat".inp[[3]] More conveniently.5 no 101. list(id="". The scan() function Next: Accessing builtin datasets . byrow=TRUE) There are more elaborate input facilities available and these are detailed in the manuals. 36 de 99 25/02/2011 10:36 . and hence. header=TRUE) where the header=TRUE option specifies that the first line is a line of headings.inp$x.inp$id..inp$y or the list may be attached at position 2 of the search path (see Attaching arbitrary lists ). For example > inp <. Input file form without row labels: Price 52. case the file may omit the row label column as in the following.read.2 no 131. The first step is to use scan() to read in the three vectors as a list. is a list whose components are the three vectors read in..00 54.googleusercontent. that no explicit row labels are given. use assignments like > label <.com/translate_c?hl=pt-BR&ie=UTF-. and the file is input. y <.50 57.scan("input. held in inp .table() function .dat". ncol=5.50 59. y=0)) If you wish to access the variables separately they may either be re-assigned to variables in the working frame: > label <. all components of which must be of the same mode as the dummy value. list("". x <. Up: Reading data from files 7. the dummy list can have named components.0 1000 5 4.scan("input.Uma Introdução ao R http://translate. as follows > inp <.matrix(scan("light.0 710 5 7. the first of mode character and the remaining two of mode numeric. To separate the data items into three separate vectors. Previous: The read.inp[[2]]. y <.dat .75 57.

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

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

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

2 Control statements 42 de 99 25/02/2011 10:36 . in particular multiple assignments are possible. be itself included in parentheses and used a part of an even larger expression. Up: Top 9 Grouping. . assuming a common continuous distribution: > ks. Up: Loops and conditional execution 9.05919 alternative hypothesis: two-sided Warning message: cannot compute correct p-values with ties in: ks. verticals=TRUE.. Previous: Probability distributions . xlim=range(A. B) Note the warning: there are several ties in each sample.test(A. We have already seen a pair of boxplots. Previous: Loops and conditional execution . expr_m } . loops and conditional execution Grouped expressions Control statements Next: Control statements . and qqplot will perform a QQ plot of the two samples. The Kolmogorov-Smirnov test is of the maximal vertical distance between the two ecdf's.007497 alternative hypothesis: true location shift is not equal to 0 Warning message: Cannot compute exact p-value with ties in: wilcox. verticals=TRUE. Os seguintes > plot(ecdf(A). Wilcoxon rank sum test with continuity correction data: A and B W = 89.googleusercontent. do. Since such a group is also an expression it may. B)) > plot(ecdf(B).Uma Introdução ao R http://translate. .test(A.test(A. Up: Loops and conditional execution 9. B) Next: Writing your own functions . which suggests strongly that these data are from a discrete distribution (probably due to rounding).points=FALSE. p-value = 0.. do. Previous: Grouped expressions . for example. There are several ways to compare graphically the two samples.com/translate_c?hl=pt-BR&ie=UTF-.points=FALSE. { expr_1 . add=TRUE) will show the two empirical CDFs. Even an assignment is an expression whose result is the value assigned.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..5962. p-value = 0. in which case the value of the group is the result of the last expression in the group evaluated. Commands may be grouped together in braces. and it may be used wherever any expression may be used.. and so on. B) Two-sample Kolmogorov-Smirnov test data: A and B D = 0.

See the help facility for further details. is as follows: > xc <. There is a vectorized version of the if / else construct. 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. 19 which will produce an array of plots corresponding to each level of the factor. a. expr_1 is a vector expression. Previous: Conditional execution . now putting all plots on the one display. This has the form ifelse(condition. b) and returns a vector of the length of its longest argument. otherwise b[i] . Up: Control statements 9. One possibility here is to use coplot() .com/translate_c?hl=pt-BR&ie=UTF-.split(y. the ifelse function. and only evaluate their second argument if necessary.. expr_2 is repeatedly evaluated as name ranges through the values in the vector result of expr_1 . This is a useful function. 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. (often a sequence like 1:20 ). The “short-circuit” operators && and || are often used as part of the condition in an if statement. suppose ind is a vector of class indicators and we wish to produce separate plots of y versus x within classes. and expr_2 is often a grouped expression with its sub-expressions written in terms of the dummy name .Uma Introdução ao R http://translate. Code that takes a `whole object' view is likely to be both clearer and faster in R. As an example.) Warning : for() loops are used in R code much less often than in compiled languages.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 9.2. && and || apply to vectors of length one. Another way to do this. with elements a[i] if condition[i] is true.. ind) > for (i in 1:length(yc)) { plot(xc[[i]].split(x. Conditional execution Repetitive execution Next: Repetitive execution . Whereas & and | apply element-wise to vectors. yc[[i]]) abline(lsfit(xc[[i]].2. Other looping facilities include the > repeat expr 43 de 99 25/02/2011 10:36 . mostly used in connection with boxplots. Previous: Control statements .2 Repetitive execution: for loops.googleusercontent. ind) > yc <.

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

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

. df) which is now equivalent to the three cases above.. An outline example is given below. if arguments to called functions are given in the “ name = object ” form. limit=20) { ...frame. df. It is important to note that defaults may be arbitrary expressions.. they are not restricted to be constants as in our simple example here.fun1(d. graph=TRUE..function(data.fun1(data=d.function(data. graph=TRUE. Thus if there is a function fun1 defined by > fun1 <. for more details on the par() function.) This can be done by including an extra argument. } it could be called as > ans <.. positional form. graph=TRUE. data. df. fun1 <.. graph. (See The par() function . Up: Writing your own functions 10.. data. and specify named arguments after the positional arguments. Next: The three dots argument . limit=20) > ans <. '.frame. for example > ans <. Up: Writing your own functions 10. Previous: Defining new binary operators .googleusercontent. . limit) { [function body omitted] } then the function may be invoked in several ways. df.) { [omitted statements] if (graph) par(pch="*". they may be given in any order. even involving other arguments to the same function. limit=10) which changes one of the defaults.frame. graph=TRUE.fun1(d.fun1(d. In many cases arguments can be given commonly appropriate default values. of the function. .Uma Introdução ao R http://translate. Previous: Named arguments and defaults . if fun1 were defined as > fun1 <.fun1(d. data.function(data. ' argumento Another frequent requirement is to allow one function to pass on argument settings to another. literally ' . limit=20..4 The ' . Next: Assignment within functions . limit=20.3 Named arguments and defaults As first noted in Generating regular sequences . Furthermore the argument sequence may begin in the unnamed.. 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..frame=df) are all equivalent.com/translate_c?hl=pt-BR&ie=UTF-. data. 20) > ans <.) 46 de 99 25/02/2011 10:36 . TRUE. or as > ans <. in which case they may be omitted altogether from the call when the defaults are appropriate. For example. which may then be passed on.

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

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

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

has been used in a function that was returned as the value of another function will the special behavior described here occur. a function for making deposits and a function for stating the current balance. For most users <<. a function for making withdrawals.amount cat(amount. "\n\n") } ) } ross <. We achieve this by creating the three functions within account and then returning a list containing them. Only when <<. in that environment. ## first evaluation in S S> cube(2) Error in sq(): Object "n" not found Largaram S> n <. <<. The special assignment operator.com/translate_c?hl=pt-BR&ie=UTF-.. "\n\n") } balance = function() { cat("Your balance is".open.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 .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 . Your balance is".googleusercontent. 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.total . "\n\n") } withdraw = function(amount) { if(amount > total) stop("You don't have that much money!\n") total <<. with the value of right hand side.function(total) { list( deposit = function(amount) { if(amount <= 0) stop("Deposits must be positive!\n") total <<. total.Uma Introdução ao R http://translate. In the following example we show how R can be used to mimic a bank account.creates a global variable and assigns the value of the right hand side to it 21 . "deposited. "withdrawn. total. they will have access to its value.. Because these functions are defined in an environment which contains total . A functioning bank account needs to have a balance or total. Your balance is". open.open. is used to change the value associated with total . If the global or top-level environment is reached without finding the symbol total then that variable is created and assigned to there. 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.account(100) robert <.account <.total + amount cat(amount. 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.. total.

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

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

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

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

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

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

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

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

~ .lm(y ~ .model <. Other functions for exploring incremental sequences of models are add1() . and is usually written eta = beta_1 x_1 + beta_2 x_2 + . Next: Generalized linear models . but with slightly different meaning. .lm(y ~ x1 + x2 + x3 + x4 + x5. of interest and stimulus variables x_1.update( old. data = production) > fm6 <. Previous: Updating fitted models . only . y. whose values influence the distribution of the response. This linear function is called the linear predictor .update(fm6..formula ) In the new. .Uma Introdução ao R http://translate. fit an additional model including a sixth regressor variable. + x6) > smf6 <. data = production) would fit a model with response y and regressor variables all other variables in the data frame production . new. The stimulus variables influence the distribution of y through a single linear function.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. Por exemplo > fmfull <.update(fm05.. ' . .formula the special name consisting of a period. > fm05 <. sqrt(.) would fit a five variate multiple regression with variables (presumably) from the data frame production . drop1() and step() .) ~ . The name ' . ' can also be used in other contexts. 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. Up: Statistical models in R 11. '.. . phi)) 59 de 99 25/02/2011 10:36 .. but for full details see the on-line help.. A generalized linear model may be described in terms of the following sequence of assumptions: There is a response. x_2.googleusercontent. hence x_i has no influence on the distribution of y if and only if beta_i is zero. The names of these give a good clue to their purpose.gamma(lambda(mu))) + tau(y. mu. Por exemplo.model . Next: Nonlinear least squares and maximum likelihood models .. only. + beta_p x_p. Previous: Analysis of variance and model comparison . Up: Statistical models in R 11.6 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. and fit a variant on the model where the response had a square root transform applied. Its form is > new. Note especially that if the data= argument is specified on the original call to the model fitting function. phi) = exp((A/phi) * (y lambda(mu) . can be used to stand for “the corresponding part of the old model formula”.com/translate_c?hl=pt-BR&ie=UTF-.

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

The names of the standard. and to estimate for each model the LD50.55.26. F(beta_0 + beta_1 x)) where for the probit case. > fitted.. supplied family generators are given under “Family Name” in the table in Families .70). data=sales) but much less efficiently. in parentheses as a parameter. the variance function may also be specified in this way. n = rep(50. The binomial family Consider a small. The first step is to set the data up as a data frame > kalythos <.frame(x = c(20. and in the logit case (the default). its use is quite simple. Note how the gaussian family is not automatically provided with a choice of links. Where there is a choice of links. that is the age at which the chance of blindness for a male inhabitant is 50%. F(z) = e^z/(1+e^z). 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.model <. both models have the form y ~ B(n. family = gaussian.generator .generator . so no parameter is allowed. this can usually be achieved through the quasi family. the effects of which become more marked with increasing age.. data = sales) achieves the same result as > fm <. from Silvey (1970). y = c(6. tested: 50 50 50 50 50 No.44)) To fit a binomial model using glm() there are three possibilities for the response: 61 de 99 25/02/2011 10:36 .35.frame ) The only new feature is the family. In the case of the quasi family.com/translate_c?hl=pt-BR&ie=UTF-. On the Aegean island of Kalythos the male inhabitants suffer from a congenital eye disease.37. If a problem requires a gaussian family with a nonstandard link. as we shall see later. Although this may seem a little complicated at first sight. artificial example. blind: 6 17 26 37 44 The problem we consider is to fit both logistic and probit models to this data. data= data.beta_0/beta_1 that is.data.lm(y ~ x1+x2. the point at which the argument of the distribution function is zero. The data is shown below: Idade: 20 35 45 55 70 No.5).googleusercontent.glm(y ~ x1 + x2.45.17. F(z) = Phi(z) is the standard normal distribution function. which is the instrument by which the family is described. Samples of islander males of various ages were tested for blindness and the results recorded. The gaussian family A call such as > fm <.glm( formula . Some examples make the process clear. If y is the number of blind at age x and n the number tested. In both cases the LD50 is LD50 = . family= family.Uma Introdução ao R http://translate. the name of the link may also be supplied with the family name.

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

1). 159.1 seem adequate. The data are: > x <.56.02.1. 0. 191.06. 0.Uma Introdução ao R http://translate.googleusercontent..05) > yfit <. 0. 200) The fit criterion to be minimized is: > fn <.c(0. Unlike linear regression for example. guess some parameter values. We seek the parameter values that minimize some index of lack-of-fit. > nlfit <.7 Nonlinear least squares and maximum likelihood models Certain forms of nonlinear model can be fitted by Generalized Linear Models ( glm() ). 0. 97. nlm() and (from R 2. and superimpose the model curve using those values.02. 0. But in the majority of cases we have to approach the nonlinear curve fitting problem as one of nonlinear optimization. hessian = TRUE) After the fitting. 107. 1.0) nlminb() . which provide the functionality (and more) of S-P LUS 's ms() and nlminb() .seq(.(p[1] * x)/(p[2] + x))^2) In order to do the fit we need initial estimates of the parameters. 123.56.1. page 51. data = biochem) The reader is referred to the manual and the help document for further information. Up: Nonlinear least squares and maximum likelihood models 11.06. Previous: Nonlinear least squares and maximum likelihood models . and out$estimate are the least squares estimates of the parameters. 47.2. p = c(200.02. variance=constant). Next: Some non-standard models . and they do this by trying out various parameter values iteratively. R's nonlinear optimization routines are optim() . 0.1 Least squares One way to fit a nonlinear model is by minimizing the sum of the squared errors (SSE) or residuals. 207.22. > plot(x.11. y) > xfit <. and convergence may depend critically upon the quality of the starting values.glm(y ~ x1 + x2 . Up: Statistical models in R 11. 0.200 * xfit/(0. 1. 0. 201.c(76. One way to find sensible starting values is to plot the data. but these starting values of 200 and 0.1 + xfit) > lines(spline(xfit. 0. 0.10) > y <. 1.. 139. Mínimos quadrados Maximum likelihood Next: Maximum likelihood . To obtain the approximate standard errors (SE) of the estimates we do: 63 de 99 25/02/2011 10:36 . as needed. .11. All the methods require initial guesses about what parameter values to try. This method makes sense if the observed errors could have plausibly arisen from a normal distribution. Now do the fit: > out <.10.7.com/translate_c?hl=pt-BR&ie=UTF-. family = quasi(link=inverse.nlm(fn. 152.22. out$minimum is the SSE. Previous: Generalized linear models . Here is an example from Bates & Watts (1988).function(p) sum((y . there is no guarantee that the procedure will converge on satisfactory estimates. yfit)) We could do better.

05) > yfit <.212. To obtain the approximate SEs of the estimates 64 de 99 25/02/2011 10:36 . Vm. 13. 1.2 Maximum likelihood Maximum likelihood is a method of nonlinear model fitting that applies even if the errors are not normal.6907. . 59.68370711 0. 1.2) * solve(out$hessian))) The 2 in the line above represents the number of parameters. Vm. 108–111.c( 6..8369.947e+00 30.c(59. out$minimum is the negative log-likelihood.seq(. 56. 62.n*log(1+exp(p[1]+p[2]*x)) + log(choose(n.nlm(fn. Error t value Pr(>|t|) Vm 2.743 1. 62.02. 53. y)) )) We pick sensible starting values and do the fit: > out <.7842. 52. The model we have just fitted is the Michaelis-Menten model.127e+02 6.93 on 10 degrees of freedom Correlation of Parameter Estimates: Vm K 0.68384222 * xfit/(0.06412146 + xfit) > lines(spline(xfit.20). y) > xfit <. 1.1. p = c(-50.7. 60) The negative log-likelihood to minimize is: > fn <. 28. or equivalently which minimize the negative log-likelihood.412e-02 8. 60. K) data: df Vm K 212.8839) > y <.c(1.57e-05 Residual standard error: 10. Here is an example from Dobson (1990). The method finds the parameter values which maximize the log likelihood. A 95% confidence interval would be the parameter estimate +/. y=y) > fit <.615 3. and out$estimate are the maximum likelihood estimates of the parameters.24e-11 K 6.. > sqrt(diag(2*out$minimum/(length(y) .281e-03 7. which clearly could also be fit by glm() . so we can use > df <. 1. 1.1.7242. 60) > n <. yfit)) The standard package stats provides much more extensive facilities for fitting non-linear models by least squares.data.8610.function(p) sum( . 1. df) > fit Nonlinear regression model model: y ~ SSmicmen(x.Uma Introdução ao R http://translate.(y*(p[1]+p[2]*x) .com/translate_c?hl=pt-BR&ie=UTF-.nls(y ~ SSmicmen(x. hessian = TRUE) After the fitting. 1. K) Parâmetros: Estimate Std. K).96 SE.449 > summary(fit) Formula: y ~ SSmicmen(x.frame(x=x. The data are: > x <.06412123 residual sum-of-squares: 1195.8113. 18. We can superimpose the least squares fit on a new plot: > plot(x. 1. 61. This example fits a logistic model to dose-response data. pp. Vm. Up: Nonlinear least squares and maximum likelihood models 11. 63.googleusercontent.7651 Previous: Least squares .7552.

These functions make heavy use of formulae to specify the models.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. implemented in user-contributed packages gam and mgcv . Rather than seek an explicit global linear model for prediction or interpretation. together with code for projection pursuit regression.. Mixed models. that is linear and non-linear regressions in which some of the coefficients correspond to random effects. for example function rlm in package MASS . The recommended nlme package provides functions lme() and nlme() for linear and non-linear mixed-effects models. 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. Up: Top 12 Graphical procedures Graphical facilities are an important and extremely versatile component of the R environment. Next: Packages . An extension is Generalized Additive 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. Previous: Nonlinear least squares and maximum likelihood models . tree-based models seek to bifurcate the data.googleusercontent. 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 . we do: > sqrt(diag(solve(out$hessian))) A 95% confidence interval would be the parameter estimate +/. Tree-based models.Uma Introdução ao R http://translate. at critical points of the determining variables in order to partition the data ultimately into groups that are as homogeneous as possible within. Additive models. Models are again specified in the ordinary linear model form. Function loess is in the standard package stats . The model fitting function is tree() . Previous: Statistical models in R . usually one for each determining variable. Up: Statistical models in R 11.1. The results often lead to insights that other data analysis methods tend not to yield. There are several functions available for fitting regression models in a way resistant to the influence of extreme outliers in the data. It is possible to use the facilities to display a wide variety of statistical graphs and also to build entirely new types of graph. Function lqs in the recommended package MASS provides state-of-art algorithms for highly-resistant fits. Less resistant but statistically more efficient methods are available in packages. Robust regression. recursively..com/translate_c?hl=pt-BR&ie=UTF-. 65 de 99 25/02/2011 10:36 . The loess() function fits a nonparametric regression by using a locally weighted regression. Local approximating regressions. and as heterogeneous as possible between. This technique aims to construct a regression function from smooth additive functions of the determining variables.

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

it produces a plot of the values in the vector against their index in the vector. 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.1. a + b + c ).googleusercontent. y ) produces a scatterplot of y against x . Up: High-level plotting commands 12. An example panel function useful for coplots is panel. If X is a numeric matrix or data frame. If c is a factor.Uma Introdução ao R http://translate. If x is a numeric vector. 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. When three or four variables are involved a coplot may be more enlightening.intervals() is useful for selecting intervals.y) xy ) If x and y are vectors. y is any object. Previous: The plot() function . The third form plots y against every object named in expr . 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). the command > pairs(X) produces a pairwise scatterplot matrix of the variables defined by the columns of X .. 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 . plot( x ) If x is a time series. x. the second form produces boxplots of y for each level of f .2 Displaying multivariate data R provides two very useful functions for representing multivariate data. The number and position of intervals can be controlled with given. The first form generates a bar plot of f . plot( x . this simply means that a is plotted against b for every level of c .values= argument to coplot() —the function co.com/translate_c?hl=pt-BR&ie=UTF-. 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. 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. plot( plot( Next: Display graphics . 67 de 99 25/02/2011 10:36 . plot( f ) plot( f . it produces a plot of imaginary versus real parts of the vector elements. 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.. When c is numeric.smooth() . y is a numeric vector. then the command > coplot(a ~ b | c) produces a number of scatterplots of a against b for given values of c . expr is a list of object names separated by ` + ' (eg. If x is a complex vector. y ) f is a factor object. this produces a time-series plot. plot( df ) plot(~ expr ) plot( y ~ expr ) df is a data frame. that is. If a and b are numeric vectors and c is a numeric vector or factor object (all of the same length).

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

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

the following code draws the formula for the Binomial 70 de 99 25/02/2011 10:36 . mtext . For example. or fill it if the graphics device allows the filling of figures. line styles... legend. Where x and y arguments are required. fill= v ) Colors for filled boxes legend( ..2.. x and y coordinates) to determine where to place the new plot elements. pch= v ) Plotting characters (character vector) title(main. colors etc. ..obj ) Adds a line of slope b and intercept a to the current plot. . and v= x similarly for the x-coordinates for vertical lines. Previous: Low-level plotting commands . Up: Low-level plotting commands 12.1 Mathematical annotation In some cases. 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. h= y may be used to specify y-coordinates for the heights of horizontal lines to go across a plot. lty= v ) Line styles legend( . are identified with the labels in the character vector legend . axis(side. as follows: legend( . y.) Draws a polygon defined by the ordered vertices in ( x . lwd= v ) Line widths legend( . counting clockwise from the bottom. Mathematical annotation Hershey vector fonts Next: Hershey vector fonts . it is also sufficient to supply a single argument being a list with elements named x and y . Also lm. in that order. and tick positions and labels. Similarly a matrix with two columns is also valid input.) which are taken as an intercept and slope. 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. .googleusercontent. polygon(x. abline(v= x ) abline( lm. y.com/translate_c?hl=pt-BR&ie=UTF-. it is useful to add mathematical symbols and formulae to a plot. Low-level plotting functions usually require some positioning information (eg. Useful for adding custom axes after calling plot() with the axes=FALSE argument. axis .. legend(x.obj may be list with a coefficients component of length 2 (such as the result of model-fitting functions. In this way functions such as locator() (see below) may be used to specify positions on a plot interactively.Uma Introdução ao R http://translate. This can be achieved in R by specifying an expression rather than a character string in any one of text .) 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. or title .... y ) and (optionally) shade it in with hatch lines. col= v ) Colors in which points or lines will be drawn legend( .) Other arguments control the positioning of the axis within or beside the plot. Plotting characters. sub) Adds a title main to the top of the current sub at the bottom in a smaller font.) Adds a legend to the current plot at the specified position.

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

its position in the x / y vectors) plotted nearby. Previous: Interacting with graphics . affecting all graphics functions which access the current device. When the process is terminated (see above). For example.. Graphics parameters can be set in two ways: either permanently. Previous: Using graphics parameters . affecting only a single graphics function call. and each device has a default set of parameters when initialized. or temporarily. par(c("col". identify() returns the indices of the selected points.Uma Introdução ao R http://translate. returns a list of all graphics parameters and their values for the current device. customize almost every aspect of the display using graphics parameters . Alternatively. you can use these indices to extract the selected points from the original vectors x and y .. "lty")) With a character vector argument. rather than their positions. figure arrangement and text justification among many others. however. button) by plotting the corresponding component of labels nearby (or the index number of the point if labels is absent).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. sets the values of the named graphics 72 de 99 25/02/2011 10:36 . which controls colors. y) The identify() functions performs no plotting itself.) par(col=4. Next: Graphics parameters . we could use the identify() function as follows: > plot(x. we may wish the user to select some observation of interest from a graphical display and then manipulate that observation in some way. colors.com/translate_c?hl=pt-BR&ie=UTF-. lty=2) With named arguments (or a single list argument). Every graphics parameter has a name (such as ` col '. Up: Using graphics parameters 12. particularly for presentation or publication purposes. You can. Returns the indices of the selected points when another button is pressed. Given a number of (x. y) coordinates in two numeric vectors x and y . you could use some informative string (such as a case name) as a highlight by using the labels argument to identify() . y) > identify(x. returns only the named graphics parameters (again. Sometimes we want to identify particular points on a plot. par() Without arguments.4 Using graphics parameters When creating graphics. Up: Graphics 12.4. but simply allows the user to move the mouse pointer and click the left mouse button near a point. or disable marking altogether with the plot = FALSE argument. R maintains a list of a large number of graphics parameters which control things such as line style.googleusercontent. as a list.) and a value (a color number. R's defaults do not always produce exactly that which is required. If there is a point near the mouse pointer it will be marked with its index number (that is.) A separate list of graphics parameters is maintained for each active device. for example. The par() function Arguments to graphics functions Next: Arguments to graphics functions .

and returns the original values of the parameters as a list... 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 restoring the initial values when plotting is complete. > par(oldpar) To save and restore all settable 23 graphical parameters use > oldpar <. lty=2) .4.2 Temporary changes: Arguments to graphics functions Graphics parameters may also be passed to (almost) any graphics function as named arguments. even when par() is called from within a function. that is.googleusercontent.readonly=TRUE) .. Note that axes is not a graphics parameter but an argument to a few plot methods: see xaxt and . without changing the default plotting character for future plots.com/translate_c?hl=pt-BR&ie=UTF-. Setting graphics parameters with the par() function changes the value of the parameters permanently . Note that calls to par() always affect the global values of graphics parameters. > par(oldpar) Previous: The par() function . which will be used by all graphics functions unless an alternative value is given. this is not implemented entirely consistently and it is sometimes necessary to set and reset graphics parameters using par() . yaxt 73 de 99 25/02/2011 10:36 .. this is provided as a somewhat more detailed alternative. and then restore the original values so as not to affect the user's R session. plotting commands .Uma Introdução ao R http://translate. plotting commands . Up: Using graphics parameters 12. Previous: Using graphics parameters . in the sense that all future calls to graphics functions (on the current device) will be affected by the new value. Up: Graphics 12. Graphics parameters will be presented in the following form: name = value A description of the parameter's effect. y. This is often undesirable behavior—usually we want to set some graphics parameters. > oldpar <. value is a typical value you might use when setting the parameter.. do some plotting. parameters. Por exemplo: > plot(x.par(no.5 Graphics parameters list The following sections detail many of the commonly-used graphical parameters. You can think of setting graphics parameters in this way as setting “default” values for the parameters.. the argument name to use in calls to par() or a graphics function. Next: Device drivers . pch="+") produces a scatterplot using a plus sign as the plotting character. The R help documentation for the par() function provides a more concise summary. name is the name of the parameter.. Unfortunately.par(col=4. except that the changes only last for the duration of the function call...

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

googleusercontent. Use tck=0. When tck is small (less than 0.) and (usually) bounded by the axes themselves. Positive numbers measure outside the plot region. 7. the tick marks (which mark off unit divisions along the axis line) and the tick labels (which mark the units. the proportion of text that appears to the left of the plotting position. The second component is the distance to the tick labels.sub The character expansion to be used for axis annotation. 12) The first two numbers are the desired number of tick intervals on the x and y axes respectively. tck=0. cex=1. x and y labels. and the final component is the distance from the axis position to the axis line (usually zero). 0 means always parallel to axis. 1 means always horizontal. Negative values give tick marks outside the plotting region. in characters (including the decimal point.2 Axes and tick marks Many of R's high-level plots have axes. in text lines. Next: Figure margins . Previous: Graphical elements .-1.Uma Introdução ao R http://translate.axis cex. A value of 1 gives grid lines.5 Character expansion.. Graphics parameters controlling figure layout include: 75 de 99 25/02/2011 10:36 . Up: Graphics parameters 12. mgp=c(3. respectively. 1. negative numbers inside. as a fraction of the size of the plotting region. however style "r" leaves a small amount of space at the edges. Previous: Axes and tick marks .) These components can be customized with the following graphics parameters. 0) Positions of axis components.5. cex.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. etc. With styles "i" (internal) and "r" (the default) tick marks always fall within the range of the data.) 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. The first component is the distance from the axis label to the axis position. and 2 means always perpendicular to the axis.01 Length of tick marks.5.5.1 leaves a gap of 10% of the text width between the text and the plotting position. Axes have three main components: the axis line (line style controlled by the lty graphics parameter).5) the tick marks on the x and y axes are forced to be the same size. and you can construct axes yourself with the low-level axis() graphics function. lab=c(5. The third number is the desired length of axis labels.main cex. so a value of -0. respectively.com/translate_c?hl=pt-BR&ie=UTF-. titles. Up: Graphics parameters 12.0) for internal tick marks. (S has other styles not implemented in R.lab cex.) Next: Multiple figure environment . main and sub-titles. The value is the desired size of text characters (including plotting characters) relative to the default text size..01 and mgp=c(1.

as a percentage of the page measured from the bottom left corner.83: if there are three or more of either rows or columns. fig=c(4.66. Like mar and mai . 4) Set the size of a multiple figure array. the figure shows the page after four plots have been drawn. the right-hand margin is rarely needed. The example value would be for a figure in the bottom right of the page.2) . the first measures in text lines and the second in inches. 0. left. and neither is the top margin if no title is being used. Furthermore. measured in inches. The default values chosen for this parameter are often too large. Setting either of these can reduce the base size of symbols and text (controlled by par("cex") and the pointsize of the device).. 1. mai=c(1. The bottom and left margins must be large enough to accommodate the axis and tick labels. 4)/10 Position of the current figure on the page. 2) Position of the current figure in a multiple figure environment. 0. 2.4 Multiple figure environment R allows you to create an n by m array of figures on a single page. The only difference between these two parameters is that setting mfcol causes figures to be filled by column. Up: Graphics parameters 12.5. mar=c(4. top and right margins. 2) mfrow=c(2. and the array of figures is optionally surrounded by an outer margin . 9. 1) Similar to mai . the last two are the number of rows and columns in the multiple figure array. the second is the number of columns. Previous: Figure margins . 3. 0. mfg=c(2. Values are the positions of the left. 3. The first value is the number of rows.5.googleusercontent. If you want to add a figure to a current page. You can even use different values for the last two numbers than the true values for unequally-sized figures on the same page. however this may not be enough when many figures share the same page. 0) omi=c(0. starting with the bottom margin and working clockwise. respectively. 2. right. the default is chosen without regard to the size of the device surface: for example. mfrow fills by rows. When multiple figures are in use (see below) the margins are reduced. as shown in the following figure. 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. 0) Widths of the bottom. 2.Uma Introdução ao R http://translate.com/translate_c?hl=pt-BR&ie=UTF-.5. oma=c(2.8. 0. The graphical parameters relating to multiple figures are as follows: mfcol=c(3. bottom and top edges respectively. mar except the measurement unit is text lines. In a layout with exactly two rows and columns the base size is reduced by a factor of 0. Each figure has its own margins. Set this parameter to jump between figures in the array. Set this parameter for arbitrary positioning of figures within a page.. the reduction factor is 0. use new=TRUE as well (unlike S). 0) Size of outer margins. and mai are equivalent in the sense that setting one changes the value of the other. 76 de 99 25/02/2011 10:36 . The first two numbers are the row and column of the current figure. The layout in the Figure could have been created by setting mfrow=c(3. 0.

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

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

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

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

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

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

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

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

. in non-interactive use one of these must be specified or implied by some other option (see below). this also includes --no-Rconsole .) RHOME Print the path to the R “home directory” to standard output and exit successfully.) into this directory. -f file --file= file Take input from file : ' . Apart from the front-end shell script and the man page. --version Print version information to standard output and exit successfully.' means stdin . This is useful when running R from within Emacs using the ESS (“Emacs Speaks Statistics”) package.) --no-readline (UNIX only) Turn off command-line editing via readline . but not together with -f or --file . --no-site-file . --restore --no-restore --no-restore-data Control whether saved images (file . See The command-line editor . Implies --no-save unless --save has been set. One or more -e options can be used. ( --encoding enc is also accepted. --help -h Print short help message to standard output and exit successfully.Rhistory in the directory where R was started. --vanilla Combine --no-save . --no-init-file and --no-restore . --min-vsize= N --max-vsize= N 85 de 99 25/02/2011 10:36 .RData in the directory where R was started) should be restored at startup or not. This option also affects tilde-expansion: see the help for path. The default is to restore.com/translate_c?hl=pt-BR&ie=UTF-. -e expression Use expression as an input line. This needs to be an encoding known to iconv : see its help page. --save --no-save Control whether data sets should be saved or not at the end of the R session. etc. --no-init-file Do not read the user's profile at startup. for more information..expand .) --no-restore-history Control whether the history file (normally file . Under Windows. Implies --no-save unless --save has been set. --no-Rconsole (Windows only) Prevent loading the Rconsole file at startup. Command-line editing is enabled by default interactive use (see --interactive ). If neither is given in an interactive session. packages. --encoding= enc Specify the encoding to be assumed for input from the console or stdin . R installation puts everything (executables. the user is asked for the desired behavior when ending the session with q() . (There is a limit of 10.000 bytes on the total length of expressions used in this way. --no-environ . ( --no-restore implies all the specific --no-restore-* options. The default is to restore. but can be set by the environment variable R_HISTFILE ) should be restored at startup or not. --no-environ Do not read any user file to set environment variables.googleusercontent.Uma Introdução ao R http://translate. --no-site-file Do not read the site-wide profile at startup.

possible values for type are ' X11 ' (the default) and. Currently the maximum value accepted is 100000.googleusercontent. (The default is to deduce that R is being run interactively if and only if stdin is connected to a terminal or pty .) Using -e .5Gb 24 and the amount of physical RAM in the machine. Currently. `Mega' (2^20). --max-ppsize= N Specify the maximum size of the pointer protection stack as N locations. (For back-compatibility. This defaults to 10000. It implies --quiet and --no-save . but can be increased to allow large and complicated calculations to be done. or regular `kilo' (1000).. and usually 56 bytes on a 64-bit machine. Warning and error messages are sent to the error channel ( stderr ). further command line options are disregarded. Specify the minimum or maximum amount of memory used for variable size objects by setting the “vector heap” size to N bytes. Here. provided that ' Tcl/Tk ' support is available. or ' k '. A cons cell takes 28 bytes on a 32-bit machine.. and in particular set R's option verbose to TRUE . --max-mem-size= N (Windows only) Specify a limit for the amount of memory to be used both for R objects and working areas.Uma Introdução ao R http://translate. ' Tk '. ' K '. Note that input and output can be redirected in the usual way (using ' < ' and ' > '). --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 . meaning `Giga' (2^30). --gui= type -g type (UNIX only) Use type as graphical user interface (note that this also includes interactive graphics). R code uses this option to control the printing of diagnostic messages. --verbose Print more information about progress. --quiet --silent -q Do not print out the initial copyright and welcome messages. This option is intended to support programs which use R to compute results for them. 86 de 99 25/02/2011 10:36 . ' x11 ' and ' tk ' are accepted. N must either be an integer or an integer ending with ' G '. --slave Make R run as quietly as possible. -f or --file asserts non-interactive use even if --interactive is given. This is set by default to the smaller of 1.com/translate_c?hl=pt-BR&ie=UTF-. See the previous option for details on N . (computer) `Kilo' (2^10). --ess (Windows only) Set Rterm up for use by R-inferior-mode in ESS . --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.) --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) . ' M '. and must be between 32Mb and the maximum allowed on that version of Windows. and should instead be given when starting the R executable from inside the debugger. --debugger= name -d name (UNIX only) Run R through debugger name . For most debuggers (the exceptions are valgrind and recent versions of gdb ). including asserting interactive use without the command-line editor. but the line length limit of 4095 bytes still applies.

REMOVE Remove add-on packages.googleusercontent. LINK (UNIX only) Front-end for creating executable programs. INSTALL Install add-on packages. 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. A forma geral é R CMD command args where command is the name of the tool and args the arguments passed on to it. Rd2txt can be used as shorthand for Rd2conv -t txt . Currently. LaTeX. 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. BATCH Run R in batch mode. the following tools are available. and extracting the examples. SHLIB Build shared library for dynamic loading. plain text... but not intended to be called “directly”. 87 de 99 25/02/2011 10:36 .Uma Introdução ao R http://translate. R. build Build (that is. including HTML . Rd2pdf can be used as shorthand for Rd2dvi --pdf . Rdconv Rd2txt Convert Rd format to various other formats.com/translate_c?hl=pt-BR&ie=UTF-. package) add-on packages. The command R CMD allows the invocation of various tools which are useful in conjunction with R. Rprof Post-process R profiling files. COMPILE (UNIX only) Compile files for use with R. check Check add-on packages. Rd2dvi Rd2pdf Convert Rd format to DVI/PDF.

The command-line setting overrides the setting in the user's Rconsole file. Failing all those. If the environment variable R_USER is defined.com/translate_c?hl=pt-BR&ie=UTF-. After those two user-controllable settings. For example. R tries to find system defined home directories.pl ) with several environment variables set appropriately.. and environment variables HOMEDRIVE and HOMEPATH are defined (and they normally are) these define the home directory.pl the appropriate interpreter (if available) is called to run it. PATH . invoking by R. that gives the home directory. In addition.exe or more directly by Rterm. --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.Uma Introdução ao R http://translate.exe . the methods described in the previous section may be used. including R_HOME . Previous: Invoking R from the command line .. . and trigger a break to the debugger during command line processing.sh or . if the environment variable HOME is defined. (This mechanism is used for drag-and-drop and file association with RGui.Debug Enable the “Break to debugger” menu item in Rgui . If the named file does not exist it sets the working directory if the parent directory exists. BSTINPUTS and TEXINPUTS . If that fails.) The following additional command-line options are available when invoking RGui. TMP and TEMP are either unset or one of them points to a valid place to create temporary files and directories.) For interactive use. It first tries to use the Windows "personal" directory (typically C:\Documents and Settings\username\My Documents in Windows XP). If there is an argument ending . It will be run under the appropriate interpreter (Perl for . graphics and pager). but references to the `home directory' need to be clarified.exe .exe .sh or . the home directory is taken to be the starting directory. .googleusercontent. R_OSTYPE . or if it has extension . but also works for Rterm. Up: Invoking R B.exe ). . Next: Invoking R under Mac OS X .2 Invoking R under Windows There are two ways to run R under Windows. as this is not always defined on Windows.exe .exe or a more capable shell). You need to ensure that either the environment variables TMPDIR . The startup procedure under Windows is very similar to that under UNIX. Under Windows cmd can be an executable or a batch file.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. there is a console-based GUI ( Rgui. for example to run ldd or pdflatex . that gives the home directory. if 88 de 99 25/02/2011 10:36 . Environment variables can be supplied as ' name = value ' pairs on the command line.exe .bat . Next. (These are principally intended for batch use.pl file. 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. Within a terminal window (eg cmd. Under Windows with R CMD you may also specify your own .

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

28 3.40 2.. EOF but here stdin() refers to the program source and "stdin" will not be usable. an inbuilt command line editor allowing recall. use #! /usr/bin/env Rscript .70 and stdin() refers to the script file to allow such traditional usage. When using R with readline capabilities. 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.70 3. are typed by holding down <META> 26 and pressing <b>..37 3. Control characters. you could type <ESC><b>.) . Very short scripts can be passed to Rscript on the command-line via the -e flag. It can be disabled (useful for usage with ESS 25 ) using the startup option --no-readline ... 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.95 3.10 3.exe . and are written as Cm below.40 2.40 3.40 3. . such as Meta-b .77 3.60 3.03 3.Uma Introdução ao R http://translate.70 2. Up: Top Appendix C The command-line editor C.80 2. It is commonplace to write R scripts with segments like chem <. At least in Bourne and bash shells.com/translate_c?hl=pt-BR&ie=UTF-.scan(n=24) 2. editing and re-submission of prior commands is used.googleusercontent.. the #! mechanism does not allow extra arguments like #! /usr/bin/env Rscript --vanilla . Thus.40 2. use "stdin" as a file connection. Previous: Invoking R . and the file README.Rterm for command-line editing under Rterm. and written as Mb in the following. One thing to consider is what stdin() refers to. the functions described below are available. to enter Mb .. are obtained by holding the <CTRL> down while you press the <m> key. such as Control-m ..20 5.70 3.20 3. you can still type Meta characters using two-character sequences starting with ESC .1 Preliminaries When the GNU readline library is available at the time R is configured for compilation under UNIX. Many of these use either Control or Meta characters.03 28. If your terminal does not have a <META> key enabled. The ESC character sequences are also allowed on terminals 90 de 99 25/02/2011 10:36 .. Next: Function and variable index . If you want to refer to the process's stdin .50 2.50 3. Meta characters. eg scan("stdin".70 2. 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).90 3. Windows versions of R have somewhat simpler command-line editing: see ' Console ' under the ' Help ' menu of the GUI .

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

0..com/translate_c?hl=pt-BR&ie=UTF-. Mc Change the rest of the word to upper case.First : Customizing the environment .: 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 . Md Delete the rest of the word under the cursor. As from R 2. : Updating fitted models . and “save” it.Last : Customizing the environment / : Vector arithmetic : : Generating regular sequences :: : Namespaces ::: : Namespaces < : Logical vectors <<. Ml Change the rest of the word to lower case.: Vector arithmetic .inputrc file.Uma Introdução ao R http://translate. The final <RET> terminates the command line editing sequence. <RET> Re-submit the command to R. The readline key bindings can be customized in the usual way via a ~/. and “save” it. Cy Insert (yank) the last “saved” text here..12. Previous: The command-line editor . that is by including a section like $if R "\C-xd": "q('no')\n" $endif Next: Concept index . 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 . Ck Delete from cursor to end of command. these customizations can be conditioned on application R .googleusercontent. Ct Transpose the character under the cursor with the next.

com/translate_c?hl=pt-BR&ie=UTF-.list : Multiple graphics devices dev.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.frame : Making data frames as.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.googleusercontent.off : Multiple graphics devices dev.next : Multiple graphics devices dev.Uma Introdução ao R http://translate.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 .prev : Multiple graphics devices dev.data..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. 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..

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.nan : Missing values jpeg : Device drivers ks..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.search : Getting help help.com/translate_c?hl=pt-BR&ie=UTF-.na : Missing values is.googleusercontent.Uma Introdução ao R http://translate.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 ..

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 .Uma Introdução ao R http://translate. 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..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.com/translate_c?hl=pt-BR&ie=UTF-.googleusercontent.table : The read..

Uma Introdução ao R http://translate.test : One.and two-sample tests windows : Device drivers X11 : Device drivers | : Logical vectors || : Conditional execution ~ : Formulae for statistical models Next: References ..test : One. 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 vcov : Generic functions for extracting model information vector : Vectors and assignment while : Repetitive execution wilcox.test : One. t : Generalized transpose of an array T : Logical vectors t. Previous: Function and variable index .googleusercontent..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.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 .com/translate_c?hl=pt-BR&ie=UTF-.

com/translate_c?hl=pt-BR&ie=UTF-.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 .googleusercontent.. 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..and two-sample tests : One.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.Uma Introdução ao R http://translate.

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

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