Sie sind auf Seite 1von 13

STATISTICS

UNIT-1 INTRODUCTION OF STATISTICS AND ITS APPLICATION Introduction : Statistics is a subject which is very much useful for decision making purpose in almost every field of life .The process of decision making is described in following diagram. Collection of data presenting data Analysis of dataTake decision

Meaning of statistics: Origin and development of statistics : The word statistics seems to have been derived from the Latin word status or the Italion word statistia or the German word statistik . Each of these word means political state. In ancient times government used to called the information regarding the population, property of wealth of the country to have an idea of the manpower of the country and to provide bases for introducing new taxes. Definitions of statistics: Statistics has been defined differently by different authors from time to time . Statistics is mostly defined in two ways. 1. Statistics as data (plural sense) : i.e numerical statement of facts.:- More exhaustive definition is given by Prof. Horce Secrist . He has define statistics as By statistics we mean aggregate of facts affected to a marked extent by multiplicity of causes , numerically expressed , enumerated or estimated according to reasonable standards of accuracy, collected in systematic manner for a predetermined purpose and placed in relation to each other. Thus in plural sense, statistics refers to facts which are expressed in figures or simply data e.g Statistics of production, Statistics of unemployment , Statistics of national income , figure related to population , figure related to production of wheat in India in different year. 2. Statistics as statistical method (singular sense) i.e principles and techniques used in collecting and analysing such data.:- Adequate definition is given by Croxton and Cowden . According to them statistics defined as The science which deals with the collection, analysis and interpretation of numerical data Thus in singular sense statistics refers to processing techniques which are applied on raw data to get information e.g percentages , averages and coefficient denied from numerical facts are included in the term statistics in singular sense. Functions of statistics: Important functions of statistics are; 1. To present the facts in proper form. : One of the most important function of statistics is to present general statements in a precise and definite form. 2. To simplify unwieldy and complex data and to make them easily understandable. : The raw data is often unwieldy and complex. The purpose of statistical methods is to simplify large bodies of numerical data to make them more intelligible. 3. To help classification of data : Classification is a process of arrangement of numerical data according to various characteristics possessed by the data. Classification facilitates comparison and interpretation . 1

4. To provide techniques for making comparisons: The chief object of statistics is to facilitate a comparative study of various phenomena. The significance of certain figures can be appreciated when they are compared with others for the same type. 5. To enlarge individual experience. 6. To formulate policies in different fields. 7. To study the relationships between different phenomena: Certain statistical measures such as coefficient of correlation , coefficient of association , regression , etc., establish relationship between different types of data. 8. To indicate trend behaviour : The statistical techniques for extrapolation, time series and forecasting are highly useful for estimating future events. 9. To measure uncertainty: Statistical technique called probability is used to ascertain the chance of the occurrence of an event. 10. To test the hypothesis : Statistical methods are extremely used in formulating and testing hypothesis and to develop new theories. 11. To draw valid inferences. : Statistical tests are devised to help in drawing valid inference in regard to the nature and characteristics of the universe on the basis of the sample. Specific uses of statistics: In Economics :The uses of statistical methods in economics can be examined under some broad heads: 1. Formulation of Economic Laws : The inductive method of generalization is based on the observation of economic behaviour of a large number of units . For example, Engels law of consumption was based on the study of family budget in a town , The Revealed Preference Analysis of Prof. Samuelson is based on actual observation of the behaviour of buyers in the market. 2. Study of Economic Problems : Statistical data and methods are used in the proper understanding of economic problems like volume of trade, output of industries, wages, prices, bank deposits , unemployment , disparities in the distribution of income and wealth. Financial Statistics is extensively used in the fields of money and banking, credit , consumer finance and public finance. 3. Compilation of National Income Accounts : The data is systematically collected and classified into certain functional areas , geographical regions sector of the economy so as to reveal the state of economy , the degree and the direction of change and relation between them on a continuing basis. 4. Economic planning : Employment statistics in our country are still incomplete and unreliable. The information on the past period is collected and used for projections into the future. Forecasting techniques are used for this purpose. Econometric models based on statistical analysis are used for maximum exploitation of available resources.

In business :Statistical methods are widely used in business planning. 1. Location and size decision : A decision on location from amongst various alternative places will depend on the collection and analysis of information on the availability and cost of land , labour , raw materials etc.. 2. Study of demand : Statistical methods are extremely helpful in preparing trend lines leading to reliable forecasting. For market survey and research , the correlation and regression analysis are there for judging the effectiveness of various sales promotion measures. The study of time series helps in detecting cyclical and seasonal behaviour of demand and making the sales forecasts more meaningful. 2

3. production Planning : In order to avoid unnecessary loss the production schedule has to be related with sales forecasts. The raw material procurement and stocking has also to be related to the production plan . Statistical methods facilitate to calculate the most economic levels of ordering material. Graphic devices can be used for displaying sales, production and the supply of material on a time scale . 4. Quality control : The quality of a product can also be judged by statistical methods . There are two broad types of control : (i) Process control (ii) Product control . Under the process control it is ensured that the whole production process is under control. Under the product control the additional question is ask whether the entire lot from which the sample has been drawn is to be accepted or rejected. 5. Marketing decision: These decisions are related to the sales of the products . The sales of products by markets have to be tabulated chronologically or in time order. 6. Planning Future Operations : Capital investment in plant and equipment required long-term forecast about sales , prices, material costs, etc. 7. Inventory Control : It helps in coordinating production on one hand and sales on the other. 8. Personal Administration : An important use of statistics is in testing the usefulness of a person to the business in items of his interest , aptitude and capacity to work. 9. Accounts and Auditing.: The use of statistics in accounting and auditing can be appreciated better in the context of the nature of accounting records. Accounting information are very precise ,it is exact to the last paisa . But for decision making purpose such precision is not necessary and hence the statistical approximations are sought. 10. Operation Research : The common O.R problems are connected with decisions on transportation, profit maximization , cost minimization , optimum inventory level, etc. The theory of probability , expected value, theoretical distributions, Other techniques of drawing inference , Linear programming , Game theory, Critical path method (CPM), programme Evaluation and Review Techniques (PERT) are used in working out the problems. Limitations of statistics: The following are some important limitations of statistics : 1. Statistics does not study individual events.: It deals with the aggregate of facts and does not give any specific recognition to individual item of the series. Individual items, taken separately, does not constitute statistical data and are meaningless for any statistical inquiry. 2. Statistics does not study qualitative phenomenon: Qualitative phenomena like honesty , poverty , wisdom, etc which cannot be expressed numerically , are not capable for direct statistical analysis. 3. Statistical results are true only on an average. Sometimes the average or trend indicated by statistics is applied on individual cases which is not proper. 4. Statistical laws are not exact. On the basis of statistical analysis of the problem , one can talk only in terms of probability and not certainty. 5. Statistics does not reveal the entire story. The real background of the data may not be reflected in certain quantitative facts. 6. Statistical relation do not necessarily bring out the cause and effect relationship between phenomena. 7. Statistics is collected with a given purpose and cannot be indiscriminately applied to any situation. 3

8. Statistics is liable to be misused..: the use of statistical tools by inexperienced and untrained persons might lead to very fallacious conclusions. Characteristics of statistical data 1. They should be aggregate of facts:- It means that the single fact , even though numerically stated, can not be called statistics. A group idea is always involved in all statistical study to have comparative idea. e.g if it is states that the monthly expenditure of family A is Rs. 1000/- this is not statistics . A single figure does not say anything . If we also say that monthly expenditure of family B is Rs. 1500/- . Now this figures can be compared with family A. So these will be known as statistics. Similarly a single figure of production , sale purchase , import, export, birth, death, accident etc., can not be regarded as statistics but aggregate of such figure will be called statistics. 2. They should be numerically expressed :- This means that the facts to be called statistics must be expressed in numbers. Qualitative words like good , average poor, fair, young, bad, beauty etc., can not be called statistics unless a numerical value is assign to each such words, e.g good ,average and poor students are qualitative expressions and so they are not statistics. But if we assign a numerical value to each such words as , students who gets marks above 60% are good ,student who got marks between 40% and 60% are average and student who got below 40% are poor. Then they are called statistics. 3. They should be collected in systematic manner :- The data must be collected in systematic manner according to a well prepared plan. If the data are collected in a wrong manner they cannot be called statistics. In such case there will be waste of time , energy and money. 4. They should be placed in relation to each other.:- It means that they should be comparable . If comparison is not possible , figures cannot be called statistics e.g the population of in India 1971 may be compared with the population of other countries like China, UK of 1971. But it would be meaningless to compare the height of person with the height of tree. 5. They should be collected for a predetermined purpose.:- The purpose of the inquiry should be stated clearly before actually going for data collection. 6. They should be affected to a marked extent by multiplicity of causes:- Statistics are affected to a marked extent by large number of causes e.g. Statistics of prices are affected by condition of demand , supply , import, export , currency in circulation etc., Similarly statistics of production of crop are affected by a number of factors like rainfall, quality of soil , seeds and fertilizers , method of cultivation etc.. 7. They should be enumerated or estimated according to reasonable standard of accuracy.:- This means margin of error must be minimum. A reasonable standard of accuracy must be maintain in collection of statistical data. e.g An estimate that one lakh people attended Lal Krishna Advani election meeting does not mean exactly one lakh , it may be few hundred less or more. But if we are counting 100 students in a class , they must be 100.

Collection of Data : As point out earlier , Statistics are a set of numerical data. Also according to definition of Statistics in singular sense to initialize any Statistical inquiry , the method of collection of data forms foundation. Thus the raw material of Statistics always originates from the operation of counting or measurement of phenomena under study . The person who conduct the Statistical analysis is known as Respondents OR Informants . The process 4

of counting or enumeration or measurement together with the systematic recording of results is called collection of Statistical Data The collection of data refers to a purposive gathering of information relevant to the subject matter of the study from the units under investigation . the method of collection of data depends mainly upon the nature , object and the scope of inquiry on the one hand and the availability of resources and the time on the other hand. Statistical data are classified into primary and secondary depending upon the nature of data and mode of collection. Primary Data : The data which are collected for the first time by/for the investigator for his purpose , is called primary data. Secondary Data : The data which had already been collected by someone else but used by investigator for his purpose is known as secondary data. Data from primary source are collected, for the first time , keeping in view the objective of investigation. Secondary data , on the other hand , are available from certain publications or reports. The primary data collected with a specified objective of investigation , are likely to be more reliable as compared to secondary data, whenever necessary , must be done very carefully. The cost of collection of primary data , however , is much higher. Distinction between Primary and Secondary Data. Primary data Secondary data 1. The data which are collected for 1. The data which had already the first time by/for the collected by someone else but used investigator for his purpose, is by investigator for his purpose is called primary data. known as secondary data. 2. The data collected by primary 2. The data collected by secondary source is known as primary data. source is known as secondary data. 3. The investigator himself collects 3. Someone /some agency collects primary data: therefore they are secondary data therefore they are firsthand information. not firsthand information. 4. An investigator is 4. An investigator is just User of directly/indirectly Collector as well secondary data as User of primary data 5. Collection of data require more 5. Collection of secondary date time ,fund and men power or requires less time , fund and men labour. power or labour. 6. Since the primary data collected by 6. One has to examine accuracy , /for investigator they are Quite reliability , suitability and accurate ,reliable , suitable and adequency before directly using sec adequate for the purpose of inquiry. Methods for collecting Primary data: Primary data may be collected using following method 1. Direct personal investigation 2. Indirect oral investigation 3. Information from correspondents 4. Mail Questionnaire method 5. Questionnaire send through enumerators The technique of collecting data by various methods is explained below 1. Direct personal investigation Under this method, the investigator collects data by having direct contact and faceto-face approach with all informants. This method is suitable for an intensive type of investigation where 5

(i) The scope of investigation is narrow (ii) The process of investigation requires Personal attention of the investigator (iii) The investigation is confidential (iv) More emphasis is to be given to the accuracy of the data Under this method , the data may be collected by adopting any of the following two ways. (a) Interview: In this method the investigator has to contact the informants from whom the information is to be obtained directly and personally . He puts questions before them regarding the inquiry and collect the required information. The answers supplied by an informant will result in a primary data. (b) Observation : According to this method the investigator obtains the data by observing the reaction supplied by an informant as a result of treatment /action performed by an investigator on person under study. He asks no questions, but just observes the reactions in which he is interested. Observation method is particularly helpful in studying the behaviour of children , tribal, Dumb and Deaf persons and even women, because direct oral interview in their cases will not receive proper responses. This is very useful method in certain marketing studies where consumer behaviour is studied. For example , if a woman is asked whether she prefers traditional pattern of garment or modern once, she might express her liking for the traditional ones, but when both types of garments are placed before her, she may actually go for the modern ones. 2. Indirect oral investigation : This method is generally used in those cases where the information required is of a complex nature and the informants are not willing to respond, if approached directly. Here the investigator instead of directly approaching to the informants, contacts third parties known as witness capable of supplying the necessary information. Witnesses are assumed to have knowledge of required information about an actual informant. To assess reliability and accuracy of the answer provided by the witness , several witnesses have to be approached for single informant. Whereas on the other hand ,some times single witness may give information about more number of informants also. Police department for clues about the thieves and murders uses this procedure by interrogating friends or relative or third parties capable of supplying the necessary information. 3. Information from correspondents : Under this method of data collection , investigator does not collect the information himself from the person concerned directly . Investigator will appoint Local agents known as correspondents in different places of the area under investigation to collect the necessary information from their allotted territory as and when required. They will then transmit the collected information to the main investigator /central office /head quarter where the information are processed and primary data are generated. This method is more useful when an investigator requires information at regular interval of time and degree of accuracy is of secondary importance. News papers and magazine agencies , News broadcasting agencies generally adopt this method .for example , in the construction of wholesale price index number, regular information is obtained from correspondents appointed in different areas. 4. Mailed Questionnaire method : According to this method an investigator will formulate list of questions , which are directly or indirectly related with the purpose of inquiry . This list of questions either in printed / nicely written form with suitable options and sufficient spaces to answer is called Questionnaire. A questionnaire including covering letters and self addressed stamped envelope will then sent to various 6

informants through post/mailing service . In the method investigator collect the information through the filling of questionnaires by the respondents. Covering letter states, The purpose of inquiry Method ,format and understanding , if required for answering questions, Request to an informant regarding sending filled questionnaire in all respect duly back on or before deadline A word of thanks for extending co-operation towards participating information . A self addressed and stamped envelope is also enclosed for informants convenience in returning the filled questionnaire. After receiving required number of responses , processing the answers, investigator will get a primary data. 5. Questionnaire sent through enumerator The basic difference between Questionnaire and schedules is , questions in the Questionnaire is answered by informant himself in his/her own handwriting while schedule is the device of obtaining answers to the questions in a form filled by interviewer. According to this method an investigator will formulate list of questions , which are directly or indirectly related with the purpose of inquiry . An investigator will then select a team of require number of enumerators . Enumerators are provided training Aabout purpose of inquiry , method and format of furnishing answers given by informants , tactful way of checking accuracy and reliability of information on the spot by asking different additional questions , collecting supplementary information etc. Enumerators are then provided with standardized schedules or questionnaires and specific instructions are given to them regarding the manner in which schedules are to be filled. The enumerators explain clearly the object of the enquiry, the definitions of basic concept to the information and record response themselves in the questionnaire forms. An enumerator will hand over filled schedules to an investigator once they finish up their allotted task. After receiving responses , processing the answers, investigator will get a primary data. Sources of secondary data: The chief sources of secondary data may be broadly classified into the following groups.(i) Published sources (ii) Unpublished sources. (i) Published sources: There are number of national organizations and also international agencies which collect statistical data relating to business, trade, labour, consumptions , productions , industries, agriculture, income, currency and exchange , health, populations and number of socio-economic phenomena and published their findings in statistical reports on a regular basis. Below are the brief summary of these sources. (a) Official publications of Central government : (1) Office of the Registrar General and Census Commissioner of India, New Delhi (2) Directorate-General of Commercial Intelligence and Statistics-Ministry of Commerce. (3) Labour Bureau-Ministry of Labour (4) Directorate of Economics and Statistics-ministry of Agriculture and Irrigation (5) The Indian Army Statistical Organization (I.A.S.O.)-Ministry of Defense (6) National Sample Survey Organization (N.S.S.O.), Department of Statistics, Ministry of Planning (7) Central Statistical Organization (C.S.O.) Department of statistics ,Ministry of Planning 7

(8) Census data in various census reports Vital statistics of Indian , Indian Population Bulletin- all published by Registrar- General of India ( R.G.I.) (9) In addition to the above organizations a number of department in the state and Central governments like Income Tax, Department , Directorate general of Supplies and Disposals, Railway, Post and Telegraphs, Central Board of Revenues, Textile Commissioners office , Central Excise commissioners Office, Iron and Steel Controllers office and so on publish statistical reports on current problems. (b)Publications of Semi-government Statistical Organizations (1) Statistics department of the reserve Bank of India (Mumbai), which brings out an Annual Report of Bank, currency and Finance. (2) Economic department of Reserve Bank of India. (3) The institute of Economic Growth, Delhi. (4) Gokhale Institute of Politics and Economics, Poona. (5) The Institute of Foreign Trade , New Delhi. (6) The statistical material published by the institute like Municipal and District Boards, Corporations, Block and Panchayat Samitis on Vital Statistics , health, sanitation and other related subjects provides a fairly reliable and useful information. (b) Publications of Research Institutions. Individual research scholars , the different departments in the various universities of India published their findings in Indian Statistical Institute ( I.S.I ) , Kolkata and Delhi ; Indian Council of Agricultural Research ( I.C.A.R.) , New Delhi Indian Agricultural Statistics research Institute (I.A.S.R.I), New Delhi; National Council of Educational Research and Training (N.C.E.R.T),New Delhi National Council of Applied Economic research, New Delhi ; The institute of Applied Man Power Research , New Delhi ; The Institute of Labour Research ,Mumbai ; Indian Standards Institute, New Delhi (c) Publications of Commercial and Financial Institutions. Federation of Indian Chamber of Commerce and Industries (FICCI) ; Institute of Chartered Accountants of India, Trade Unions , Stock Exchanges, Bank Bodies , Co-Operative Societies , etc. publish reports and statistical material on current economic, business and other phenomena. (d) Reports of various Committees and Commissions appointed by the government. (e) Newspapers and Periodicals; (f) International Publications; United Nations Organizations (U.N.O.) World Health Organization (W.H.O) on contagious diseases Annual report of International Labour Organization (I.L.O) International Memory fund (I.M.F.) World Bank ; Economic and Social Commission for Asia and pacific (ESCAP) International Finance Corporation (I.F.C.) ; International Statistical Education Institute ; are very valued publications of secondary data. (ii) Unpublished source : The statistical data need not be always published. There are various sources of unpublished statistical material such as the records maintained by private firms or business enterprise who may not like to release their data to any outside agencies ; the various department and office of the Central and State governments; the research carried out by the individual research scholars in the universities or research institutes. 8

Classification
Definition : Before Tabulating the data , generally ,systematic arrangement of the raw data into different homogenous classes is necessary. This process of arranging the data into groups or classes according to similarities is technically called classification. Secrist has defined Classification as Classification is the process of arranging data into sequence and groups according to their common characteristics , or separating them into different but related parts. Tuttle has defined classification as A classification is a scheme for breaking a category into a set of parts, called classes, according to some precisely defined differing characteristics possessed by all the elements of the category. Functions of classification : The functions of classification may be briefly summarized as follows: 1. It condenses the data. 2. It facilitates comparisons. 3. It help to study relationship. 4. It facilitate the statistical treatment of the data. Rules for Classification: No hard and fast rules can be laid down for classification , but the following general guiding principles may be observed for good classification: 1. It should be unambiguous : The classes should be rigidly defined so that they should not lead to any ambiguity. 2. It should be Exhaustive and mutually exclusive.: The classes must be exhaustive in the sense that each and every item in the data must be belong to one of the classes. The various classes should be mutually disjoint or non-overlapping so that an observed value belongs to one and only one classes. 3. It should be stable : In order to have meaningful comparison of the results, an ideal classification must be stable i.e , the same pattern of classification should be adopted throughout the analysis and also for the further inquiries on the same subject. 4. It should be suitable for purpose: The classification must be in keeping with the objective of the enquiry. 5. It should be flexible.: A good classification should be flexible in that it should be adjustable to the new and changed situations and conditions. However, flexibility should not be interpreted as instability of classification. Base of Classification ; The bases or the criteria w.r.t which the data are classified depend on the objectives and purpose of the enquiry. The data can be classified on the following four bases 1. geographical i.e area-wise or regional 2. Chronological i.e w.r.t occurrence of time 3. Qualitative i.e w.r.t some character or attribute. 4. Quantitative i.e w.r.t numerical values or magnitudes 1. Geographical classification : As the name suggests , in this classification the basis of classification is the geographical or locational difference between the various items in the data like States, Regions, Zones , Areas, etc.Geographical classification are usually presented either in an alphabetical order or according to size or values to lay more emphasis on the important are or region. For example , the yield of agricultural output per hectare for different countries in some given period is given in the following table. 9

Table 1 AGRICULTURAL OUTPUT OF DIFFERENT COUNTRIES (in Kg. Per Hectare) Country India USA Pakistan USSR China Syria Sudan UAR

Average output 123.7 581.0 257.5 733.5 269.2 615.2 339.8 747.5

Source: Yojana: vol.XV, N0. 18, !9th Sept, page 22,

2. Chronological Classification: Chronological classification is one in which the data are classified on the basis of difference in time . The time series data, which are quite frequent in Economic and Business Statistics are generally classified chronologically, usually starting with the first period of occurrence. For example, the population of certain country for different years Table 2 POPULATION OF INDIA (in crores) Year Population 1901 23.8 1911 25.0 1921 25.2 1931 27.9 1941 31.9 1951 36.1 1961 43.9 1971 54.8 1981 68.3 1991 84.4 3. Qualitative Classification: When the data are classified according to some qualitative phenomena which are not capable of quantitative measurement like honesty ,beauty, employment , intelligence , occupation, sex, literacy, etc., the classification is term as qualitative or descriptive or attributes. In quantitative classification the data are classified according to the presence or absence of the attributes in the given data. If the data are classified into only two classes w.r.t an attribute like presence or absence , the classification is called simple. For example , classifying a given population of individuals as honest or dishonest ; male or female ; employed or unemployed and so on. Population Male Female If the given population is classified into more than two classes w.r.t a given attribute , it is called manifold classification . For example , for the attribute intelligence the various classes may be, Genius, Very intelligent , average intelligent , below average and dull . Population

10

Genius Dull

Highly intelligent

Average Intelligent Below average

Moreover , if the given population is divided into classes on the basis of simultaneous study of more than one attributes at a time , then also it is termed as manifold classification. For example classify the population by sex into two classes, males and females. Then each of these is again classified according to smoking , smokers and non-smokers Again each of these four classes are classified w.r.t a third attribute, religion into two classes , Hindu and nonHindu. Population Male Female
Smoker Non-smoker
Hindu Hindu Non-Hindu Non-Hindu

Non-smoker
Hindu Non-Hindu Hindu

Smoker
Non-Hindu

4. Quantitative classification : If the data are classified on the basis of character which is capable of quantitative measurement like age, height, weight , prices, production income, expenditure, sales profits, etc., it is term as quantitative classification. The quantitative character is called Variable and hence this classification is also sometimes called classification by variable. For example ,the earning of different stores may be classified as Table 3 DAILY EARNINGS (IN 00 RUPEES) OF 60 DEPARTMENTAL STORES Daily earnings Number of stores Up to 100 6 101-200 14 201-300 8 301-400 10 401-500 8 501-600 6 601-700 4 701-800 4 Variable : The quantitative phenomenon under study is called variable . Variables are of two kinds (i) Continuous variable (ii) Discrete variable Those variable which can take all possible values integral as well as fractional in a given specified range are termed as continuous variable. For example , the age of students in a school (in years ,months, days, hours minutes ,second) , height (in cms) , weight (in lbs or kgs. ) On the other hand those variable which cannot take all the possible values within a given specified range are termed as discrete variable. Discrete variable assumes only isolated value within some range . For example , Number of mistake per page, Number 11

of members in the family, The number of accidents on the road, etc., A study of quantitative classification is term as FREQUENCY DISTRIBUTION. FREQUENCY DISTRIBUTION The organization of the data pertaining to a variable involves the following three stages. (1) Discrete or ungrouped frequency distribution : A much better way of the representation of the data is to express it in the form of discrete or ungrouped frequency distribution where count the number of times each value of the variable occurs in the data. This is facilitated through the technique of tally bars. If the variables takes the values in a wide (large) range then the data still remain unwieldy and need further processing for statistical analysis. (2) Grouped frequency distribution : If the identity of the units about whom a particular information is collected is not relevant , nor is the order in which the observation occur, then the first real step is classifying the data into different classes (or class intervals) by dividing the entire range of the values of the variable into a suitable number of groups called classes and then recording the number of observations in each group or class. The various groups into which the values of the variable are classified are known as classes or class intervals; the length of the class interval is called the width of the classes. The two values specifying the class are called the class limits ;the larger value is called the upper class limit and the smaller value is called the lower class limit. (3) Continuous frequency distribution ;While dealing with a continuous variable it is not desirable to present the data into a grouped frequency distribution like 0-9, 1019,20-29 etc., because this classification does not take into consideration the observation between 9 to 10 , 19 to 20, so on . In such situation one should form continuous class intervals like 0-10, 10-20, 20-30 etc., the presentation of the data into continuous classes with corresponding frequencies is known as continuous frequency distribution. Basic principal for forming frequency distribution: (1) Types of classes : - The classes should be clearly defined and should not lead to any ambiguity. - They should be exhaustive and mutually exclusive so that each and every value of the variable corresponds to one and only one class (2) Number of classes: Although no hard and fast rule exists for no.of classes but it is depend upon the total frequency ,the nature of data and the accuracy aimed at. The number of classes should neither be too small nor be too large .i.e the no. of classes should not be greater than 20 and should not be less than 5. The formula given by Prof. Sturges known as Sturges rule for number of classes which is K = 1 + 3.322 log 10 N Where K = number of classes N= total frequency (3) Size of Class Interval ; size of the class interval should be inversely proportional to the number of classes . Maxi. Obs. Min. obs Class interval = Number of classes (4)Types of Classes : 12

Inclusive types classes : The classes in which both the upper and lower limit are included in the class are called inclusive classes for example 0-9, 10-19, 20-29 so on. This types of classes are used for classification of discrete grouped frequency distribution. (b) Exclusive type classes : The classes in which lower limit is included and upper limit is excluded from the class are called exclusive classes for examples 0-10,10-20, 20-30 so on. These classes are used for classification of continuous group frequency distribution.. In grouped frequency distribution there are gaps between upper and lower limit of succeeding classes then there is need to convert the classes in to exclusive type . the limits of the new exclusive type classes are called class boundaries. Upper class boundary = Upper class limit + (class width) Lower class boundary= Lower class limit + (class width) Mid value of class = (lower limit +upper limit) = (lower boundary +upper boundary) Open end classes :The classification is termed as open end classification if the lower limit of the first class or the upper limit of the last class are not specified.

(a)

13

Das könnte Ihnen auch gefallen