The word ‘data’ is plural of the Latin word ‘datum’ which means an individual fact, statistic, or piece of information. Data are the core of statistical analysis. Data can be collected mainly from two sources, Primary and secondary. Primary Data: Data collected by the investigator himself from primary sources is called primary data. It is also termed as original data because it is collected for the first time by a person who will use them. According to Horace Secrist “By primary data are meant those data which are original, that is, those in which little or no grouping has been made, the instance being recorded or itemized as encountered. They are essentially raw materials.” Secondary data. Data collected by some other person or organization for their own purpose are called secondary data. Such data are available either in published or unpublished form. For example data available in Journals, reports, Economic Survey, Budgets, Govt., RBI, Publication. Publications of Universities, Research Bodies, Trade and Professional organizations etc. are all sources of secondary data which can be used by any investigator. Distinction Between Secondary Data. Primary And According to Horace Secrist “the distinction between primary and secondary data is largely one of degree. Data which are secondary in the hands of one party may be primary in the hands of another.” Methods of Collecting Primary Data Primary data can be collected either by the census either by the census method in which each and every unit of the universe is counted (for example to know about the total wheat production in Punjab, we have to approach each and every farmer cultivating wheat) or by the sample method in which only selected units of the universe are counted. PRIMARY DATA CAN BE COLLECTED BY THE FOLLOWING METHODS: Direct Personal Investigation. Here the interviewer collects the data personally from the respondents and (persons from whom data are to be collected) thus the data are reliable. But here the data may be influence by the personal prejudices of the interviewers. Indirect Oral Observation. The information is collected indirectly from a third person called a witness. For example information regarding use of intoxicants : drugs, alcohol etc. The reliability of the data depends on the integrity and honesty of the witness. Information Through Correspondents. In this method local agents or correspondents are appointed to send the information to the principal Investigator on a regular basis. For example information regarding strikes, lock-outs, accidents in industrial establishments etc. Accuracy of the information will depend upon the degree of unbiasedness of the reporters and agents. Schedule Method. A schedule is a set of questions which are asked and filled by the enumerator himself. In this method the investigator personally goes to the respondent. This is the most accurate method but it is very costly and time consuming technique. Questionnaire Method. A formal list of questions is called a ‘questionnaire’. The data can be collected by preparing a questionnaire and getting it filled through various ways of communication viz. personal interview, mail, telephone etc., The data collected by the personal interview is comparatively more accurate as the interviewer can remove the doubts, if any, of the respondents and thus collect the data. In the mailed questionnaire method, the respondents are supposed to return by post the duly filled questionnaire. Through this method information can be collected from any place connected by post. Information can also be collected through telephone as in the case of personal interview. But everybody may not be having telephone. Moreover telephone information may be erratic and unreliable. According to W.M. Harper “The questions should be so designed that the questions fall into a logical sequence. This will enable the respondent to understand the purpose and as a result the quality of his answer may be improved.” Qualities of Good Questionnaire 1. (a) COVERING LETTER. A polite covering letter should be sent to the respondents along with the questionnaire mentioning the purpose, need, and usefulness of the information required and how it would benefit them. (b) Respondents should be ensured that the information supplied by them would be kept confidential. (c) Some inducement (compound, concessions, free gifts etc.) should be offered to ensure return of the filled questionnaire. (d) The respondents may be promised a copy, of the results of the survey, if they so desire. 2.The questions should be very short, simple and objective type. 3.The number of questions should not be very large; preferably it should be within 15 to 20. 4.Straight answers viz. Yes or No, type questions should be asked. 5.Personal questions should not be asked e.g. number of children, bankruptcy etc. 6.Questions requiring calculations like ratio, rates, percentage etc. should be avoided. 7.Instructions to the respondents regarding filling the questionnaire should be given. Units of measurements, kilograms, liters, metric tones etc. must be clearly stated Pre-Testing the Questionnaire (Or Pilot Survey) Before finalizing the questionnaire its draft should be got filled from a very small sample of informants selected from the relevant universe. After pre-testing, the questionnaire can be modified, if required, in order to collect adequate and accurate information. SPECIMEN QUESTIONNAIRE Draft a questionnaire containing 10 questions for that purpose. A. General •Name •Permanent Address Age Sex Male Female Martial status Married Unmarried B. Economic conditions 1.What is the average income of your father or guardian? 2.How many persons are dependent upon your father or guardian? 3.On an average how much money (in Rs.) per month your father or guardian sends you? 4.From economic point of view whether this amount is sufficient? 5.In comparison with your friends what is your level of expenditure? C. Study Habits 6.What is your class attendance level? 7.Whether your teachers are satisfied with your studies? 8.In addition to study in class how much time on an average you devote in the library. Reading Room and hostel? 9.On an average how much time you spend in studying other material than the subjects? 10. Generally what do you study besides your subjects and with what aim? EDITING PRIMARY DATA After collecting the data through any of the above methods, editing should be done. Editing means detecting of errors of omission and commission. Editing leads to completeness, consistency, accuracy and homogeneity of the data. CLASSIFICATION OF DATA According to L.R. Connor “Classification is the process of analyzing thing in groups of classes according to their resemblance or affinities and give expression to the unity of attributes that may subsist, amongst a diversity of individuals.” In the words of J.R. Hicks, “Classified and arranged facts speak themselves, unarranged they are as dead as mutton.” So classification is the process of arranging the data in groups of classes according to their common characteristics and similarities.