Chapter 2 — Collection of Data

Chapter 2, titled 'Collection of Data', covers the sources, methods, and instruments of data collection. It distinguishes primary and secondary data, explains personal interview, mailing, and telephone survey methods, and contrasts census with sample surveys. It also explains random and non-random sampling and the types of errors that can occur.

Primary data is collected first-hand by the researcher through an enquiry or survey, such as asking school students directly about their preferences. Secondary data has already been collected and processed by another agency and can be obtained from published sources such as government reports, newspapers, books, or websites. The same data is primary to the agency that first collects it and secondary to any later user.

The chapter describes three basic modes: (i) Personal Interviews, where the researcher conducts face-to-face interviews with respondents; (ii) Mailing (Questionnaire) Surveys, where the questionnaire is sent by mail and respondents complete and return it; and (iii) Telephone Interviews, where the investigator asks questions over the telephone. Each method has its own advantages and disadvantages in terms of cost, response rate, and reach.

The chapter lists several rules: questions should be precise and clear, unambiguous (enabling quick and correct answers), arranged from general to specific, free from double negatives (e.g., avoid 'Wouldn't you…'), not leading (giving clues about the desired answer), and should not indicate alternatives. The questionnaire should not be too long and should use easy-to-understand language.

A Census (Complete Enumeration) surveys every element of the population — for example, every household in India — and provides complete demographic data. A Sample Survey selects a smaller, representative group from the population to obtain information at a lower cost and in less time. Most statistical surveys prefer the sample method because it allows more detailed, intensive enquiries with a smaller team of enumerators.

In random sampling, every individual in the population has an equal chance of being selected. The lottery method involves writing the names of all units on paper, mixing them, and then selecting the required number one by one — for example, selecting 30 households from 300 by drawing names. Nowadays, computer programmes are also used to select random samples.

Sampling error is the difference between the sample estimate and the true population parameter; it can be reduced by taking a larger sample. Non-sampling errors — such as data acquisition errors (incorrect recording), non-response errors (respondent not contactable or refusing to answer), and sampling bias — are more serious because they are difficult to minimise even by increasing sample size. Even a Census can contain non-sampling errors.

Sampling bias occurs when the sampling plan is such that some members of the target population could not possibly be included in the sample. This means the sample does not truly represent the population, making the results unreliable.

The Census of India is conducted every ten years since 1881 and provides the most complete demographic record of the population, covering size, density, sex ratio, literacy, migration, and rural-urban distribution. The National Sample Survey (NSS), established by the Government of India, conducts nationwide surveys on socio-economic issues and releases data through reports and its quarterly journal Sarvekshana, covering literacy, employment, morbidity, consumer expenditure, and more.

According to Census 2011, the population of India was 121.09 crore, up from 102.87 crore in 2001. Census 1901 had recorded 23.83 crore, meaning India's population increased by more than 97 crore in 110 years. The average annual growth rate fell from 2.2 per cent in the decade 1971–81 to 1.97 per cent in 1991–2001 and further to 1.64 per cent during 2001–2011.

A pilot survey (also called pre-testing of the questionnaire) is a try-out conducted with a small group before the main survey. It helps in pre-testing the questionnaire to identify shortcomings in the questions, assess clarity of instructions, evaluate the performance of enumerators, and estimate the cost and time the actual survey will require.

Exit polls are surveys conducted during elections in which a random sample of voters who have just exited polling booths are asked whom they voted for. From this sample data, predictions about the election result are made. The chapter notes that exit polls do not always predict correctly, which illustrates the limitations of sampling.

Yes, the NCERT PDF for Chapter 2 (Collection of Data) is completely free on cbseprepmaster.com. No sign-up or account is required — just open the page and read or download the PDF directly.