Exam-useful questions from this chapter, grouped by marks, each with a full model answer. Try writing the answer yourself first, then check it against this one.
In CBSE 2026-27 this chapter is part of Unit 2 (Collection, Organisation and Presentation of Data) and the whole chapter is in the syllabus. The UP, Bihar, Rajasthan and MP boards also teach this NCERT book in Class 11; a large objective section (Bihar, MP) and a 10-mark question (UP) are included. The (½) and (1) marks in numerical answers show step marks.
1 1-Mark Questions
Q. What are primary data?
Answer: Data collected by the investigator himself through an enquiry, for the first time, are primary data; they are based on first-hand information.
Q. What is a variable?
Answer: Values that vary are called variables; they are shown by letters X, Y, Z.
Q. What is another name for a pilot survey?
Answer: Pre-testing of the questionnaire.
Q. What does population mean in statistics?
Answer: The totality of the items under study, to which the results of the study are intended to apply.
Q. Name the quarterly journal of the NSS.
Answer: Sarvekshana.
Q. When does sampling bias occur?
Answer: When the sampling plan is such that some members of the target population could not possibly be included in the sample.
Q. When was the first census after Independence held?
Answer: In 1951.
2 2-Mark Questions
Q. Write any four sources of secondary data.
Answer: Government reports and documents (½), newspapers (½), books written by economists (½), websites (½).
Q. What is a two-way question? Give an example.
Answer: A question with only two possible answers, yes or no (1). Example: Is the electricity supply in your locality regular? (Yes/No) (1)
Q. What is a sampling frame? Explain with the book’s example.
Answer: The list of all units of the population from which the sample is drawn (1). In the book, all 300 households of the area form the sampling frame, from which a random sample of 30 is drawn (1).
Q. What is an exit poll?
Answer: A random sample of voters leaving the polling booths is asked whom they voted for (1); the result of the election is predicted from these data, though not always correctly (1).
Q. In a study of the economic condition of agricultural labourers in Churachandpur district of Manipur, what are the population and the sample?
Answer: Population: all agricultural labourers in Churachandpur district (1). Sample: ten per cent of those agricultural labourers (1).
3 3-Mark Questions
Q. Give three differences between primary and secondary data.
Answer: • Collection: primary data are collected by the investigator himself for the first time; secondary data were collected and processed earlier by another agency. (1)
• Cost and time: primary data take more time and money; secondary data save time and cost. (1)
• Source: primary data come from surveys (interviews, mail, telephone); secondary data from government reports, newspapers, books and websites. (1)
Q. What is a pilot survey? State its usefulness.
Answer: A try-out of the ready questionnaire on a small group is a pilot survey or pre-testing of the questionnaire. (1)
Usefulness: • it gives a preliminary idea about the survey and shows shortcomings and drawbacks of the questions. (1) • It helps assess the suitability of questions, clarity of instructions, performance of enumerators and the cost and time of the actual survey. (1)
Q. (Hypothetical) The monthly savings (₹) of 4 households of a village are 10, 20, 30, 40. A sample of the households with savings 10 and 30 is taken. Find the sampling error and interpret it.
Answer: Population mean (parameter) = (10 + 20 + 30 + 40) ÷ 4 = 100 ÷ 4 = ₹25 (1)
Sample mean (estimate) = (10 + 30) ÷ 2 = 40 ÷ 2 = ₹20 (1)
Sampling error = 25 − 20 = ₹5; the sample underestimates average savings by ₹5; a larger sample can reduce this gap. (1)
Q. Distinguish between closed-ended and open-ended questions with examples.
Answer: • In a closed-ended (structured) question the respondent chooses from given options (two-way or multiple choice); in an open-ended (unstructured) one he answers in his own words. (1)
• Closed-ended questions are easy to use, score and codify, but hard to write and they restrict answers; open-ended ones allow individual answers but are hard to interpret and score. (1)
• Example: ‘Why did you sell your land?’ (four options) is closed-ended; ‘What is your view about globalisation?’ is open-ended. (1)
Q. Why are most surveys sample surveys? Give three reasons.
Answer: • A sample gives reasonably reliable and accurate information at lower cost and in shorter time. (1)
• A sample is small, so intensive enquiries can collect more detailed information. (1)
• A smaller team of enumerators is needed, which is easier to train and supervise. (1)
Q. What is non-random sampling? Give the book’s example.
Answer: • In non-random sampling all units of the population do not have an equal chance of selection; the investigator’s convenience or judgement plays an important role. (1)
• Units are selected on the basis of judgement, purpose, convenience or quota. (1)
• Example: selecting 10 of 100 households by choosing those conveniently located or known to you or your friend; bias enters the choice. (1)
Q. What are errors in data acquisition? Give two examples from the book.
Answer: • Errors that arise from recording incorrect responses are errors in data acquisition. (1)
• Table length: students’ measurements differ because of different measuring tapes and carelessness; orange prices vary by shop, market and quality, so only average prices can be considered. (1)
• Recording or transcribing mistakes: the enumerator or respondent may record 13 instead of 31. (1)
Q. In a study of cropping pattern in a village of 200 farms, 50 farms were surveyed, of which 50% grew only wheat. State the population, the sample size and the number of farms growing only wheat.
Answer: Population = all 200 farms of the village (1)
Sample size = 50 farms (1)
Only wheat = 50% of 50 = 0.5 × 50 = 25 farms (in the sample) (1)
4 4-Mark Questions
Q. State the merits and demerits of the personal interview.
Answer: Merits:
• Personal contact; the interviewer can explain the study and answer the respondent’s queries. (1)
• He can ask for important answers to be expanded; misinterpretation and misunderstanding are avoided; watching reactions gives supplementary information; highest response rate. (1)
Demerits:
• Most expensive, needs trained interviewers, takes longer. (1)
• The presence of the researcher may inhibit respondents from saying what they really think; possibility of influencing respondents. (1)
Q. Explain the mailing questionnaire method. Give two merits and two demerits.
Answer: A questionnaire is sent to each individual by mail with a request to complete and return it by a given date; online and SMS surveys are popular today. (1)
Merits: • least expensive; reaches remote areas. (½) • No influence by the interviewer, time for thoughtful answers, anonymity maintained, best for sensitive questions. (1)
Demerits: • no chance to clarify instructions, so questions may be misunderstood; cannot be used by illiterates. (½) • Low response rate: returned incomplete, not returned, or lost in the mail. (1)
Q. Give four differences between a census and a sample survey.
Answer: • Units: a census covers every unit of the population; a sample covers a representative part. (1)
• Cost and time: a census needs huge expenditure and many enumerators; a sample costs less, takes less time, needs a small team. (1)
• Information: a sample allows intensive enquiry and more detailed information. (1)
• Error: a census has no sampling error but may have non-sampling errors; a sample may have both. Example: Census of India vs NSS surveys. (1)
Q. Distinguish between sampling and non-sampling errors. Which is more serious?
Answer: • Sampling error = the difference between the sample estimate and the population parameter, e.g. 600 − 550 = 50. (1)
• Non-sampling errors arise from mistakes in collecting data: data acquisition, non-response, sampling bias. (1)
• Sampling error occurs only in samples and falls with a larger sample; non-sampling error can occur even in a census. (1)
• Non-sampling error is more serious because it is difficult to minimise even with a large sample. (1)
Q. What is random sampling? How would you select 3 of 10 students by the lottery method?
Answer: In random sampling every unit has an equal chance of being selected. (1)
• Write the names (or numbers) of all 10 students on identical slips. (1)
• Fold the slips and mix them well in a box. (1)
• Draw 3 slips one by one without looking; these 3 students form a random sample, as every student had an equal chance. (1)
Q. Write a note on the Census of India.
Answer: • The census gives the most complete and continuous demographic record of population; held every 10 years since 1881, first after Independence in 1951, last in 2011. (1)
• House-to-house enquiry covering every household; size, density, sex ratio, literacy, migration, rural-urban distribution, birth and death rates. (1)
• Data are collected and published by the Registrar General of India and used to understand economic and social issues. (1)
• Population: 23.83 crore in 1901, 102.87 crore in 2001, 121.09 crore in 2011; annual growth rate fell from 2.2% (1971-81) to 1.64% (2001-2011). (1)
Q. Information is to be collected from a person living in a remote village. Which mode is suitable and why? Also state the limits of the telephone interview.
Answer: • Suitable mode: a mailed questionnaire (if the person can read and write). (1)
• Reason: it is the only method to reach remote areas, it is the least expensive, does not influence the respondent and gives time for thoughtful answers. (1)
• If the person is illiterate, mail will not work; a personal interview by an enumerator is then needed. (1)
• Limits of the telephone: limited access as many people do not own telephones; reactions cannot be watched. (1)
Q. Explain non-response error and sampling bias with examples.
Answer: • Non-response error: occurs when the interviewer cannot contact a person listed in the sample or the person refuses to respond. (1)
• The sample observations may then not be representative. Example: many people never return a mailed questionnaire. (1)
• Sampling bias: occurs when the sampling plan is such that some members of the target population could not possibly be included. (1)
• Example: surveying only households with telephones; households without one can never be included. (1)
5 6-Mark Questions
Q. What points should be kept in mind while preparing a good questionnaire? Explain with examples.
Answer: • Short, with as few questions as possible; easy to understand, no difficult words. (1)
• An order that keeps the respondent comfortable; general to specific: first ‘Is the electricity supply regular?’ then ‘Is the increase in charges justified?’ (1)
• Precise and clear: drop ‘in order to look presentable’ and ask ‘What percentage of your income do you spend on clothing?’ (1)
• Not ambiguous: instead of ‘a lot of money on books’, give options less than ₹200, ₹200 to ₹300, ₹300 to ₹400, more than ₹400. (1)
• No double negatives: not ‘Don’t you think smoking should be prohibited?’ but ‘Do you think …?’ (1)
• No leading question (‘high-quality tea’) and no hint of alternatives (‘a job or a housewife’ becomes ‘What would you like to do after college?’). (1)
Q. Compare the three modes of data collection on the basis of their advantages and disadvantages.
Answer: Personal interview: advantages: highest response rate, all types of questions, better for open-ended questions, ambiguous questions can be clarified. (1) Disadvantages: most expensive, possibility of influencing respondents, more time-taking. (1)
Mail: advantages: least expensive, only method to reach remote areas, no influence on respondents, anonymity, best for sensitive questions. (1) Disadvantages: cannot be used by illiterates, long response time, no clarification, reactions cannot be watched. (1)
Telephone: advantages: relatively low cost, relatively less influence, relatively high response rate. (1) Disadvantages: limited use (not everyone owns a telephone), reactions cannot be watched, possibility of influencing respondents. (1)
Q. The incomes of 5 farmers of Manipur are 500, 550, 600, 650, 700. (a) Find the population mean. (b) Find the sampling error of the sample of farmers with incomes 500 and 600. (c) Find the error of the sample with incomes 650 and 700. (d) Conclude how sampling error can be reduced.
Answer: (a) Population mean = (500 + 550 + 600 + 650 + 700) ÷ 5 = 3000 ÷ 5 = 600 (formula ½, substitution ½, answer ½) (1½)
(b) Sample mean = (500 + 600) ÷ 2 = 550; error = 600 − 550 = 50 (the estimate is 50 too low) (1½)
(c) Sample mean = (650 + 700) ÷ 2 = 675; error = 600 − 675 = −75, i.e. the estimate is 75 too high (1½)
(d) Different samples from the same population give different estimates; with samples of 4 farmers the largest error is only 25 (e.g. 500, 550, 600, 650 has mean 575). So a larger sample reduces sampling error. (1½)
Q. Name the national-level statistical agencies and describe the work of the National Sample Survey Organisation.
Answer: Agencies: Census of India, National Sample Survey (NSS), Central Statistics Office (CSO), Registrar General of India (RGI), Directorate General of Commercial Intelligence and Statistics (DGCIS), Labour Bureau. (2)
NSSO:
• Established by the Government of India for nation-wide surveys on socio-economic issues; continuous surveys in successive rounds. (1)
• Data released through reports and its quarterly journal Sarvekshana. (1)
• Estimates of literacy, school enrolment, employment, unemployment, manufacturing and service enterprises, morbidity, maternity, child care, use of the public distribution system; 60th round (January-June 2004) on morbidity and healthcare, 68th (2011-12) on consumer expenditure. (1)
• It also collects details of industrial activities and retail prices, used by the Government of India for planning. (1)
Q. Distinguish between random and non-random sampling. How would you select 3 of 10 students using random number tables?
Answer: Differences:
• In random sampling every unit has an equal chance of selection; in non-random sampling it does not. (1)
• Random sampling uses no judgement (lottery, tables, computer); non-random uses judgement, purpose, convenience or quota, so bias may enter. (1)
• Example: 30 of 300 households by slips vs 10 of 100 convenient households. (1)
Using random number tables:
• Number the students 1 to 9, and the tenth 0. (1)
• Start anywhere in the table and read single digits in one direction, skipping a digit already drawn. (1)
• If an (illustrative) row 2952 … gives 2, 9, 5, students numbered 2, 9 and 5 are selected; every student had an equal chance. (1)
6 10-Mark Questions
Q. (UP Board 10 marks) State the sources of data. Describe the methods of collecting primary data and compare the census and sample methods.
Answer: 1. Sources of data (2): Primary data: collected by the investigator himself for the first time through an enquiry (asking students about a film star’s popularity). Secondary data: collected and processed by another agency; government reports, newspapers, books, websites; they save time and cost.
2. Instrument (1): questionnaire/interview schedule; short, easy, general to specific, clear, no double negatives or leading questions; closed-ended and open-ended questions; pre-tested by a pilot survey.
3. Modes (3): (a) Personal interview: face to face; highest response rate, clarification, reactions can be watched; but expensive, slow, respondents may be influenced. (b) Mail: least expensive, reaches remote areas, anonymity; but not for illiterates, low response rate. (c) Telephone: cheap, quick, clarification possible; but limited access, reactions cannot be watched.
4. Census vs sample (3): a census covers every unit (Census of India, every 10 years, 121.09 crore in 2011); a sample covers a representative part (10% of labourers in Churachandpur). A sample is cheaper, quicker, allows intensive enquiry with a small trained team; a census has no sampling error but huge cost. A sample may be random (lottery) or non-random (convenience, quota).
5. Conclusion (1): the choice of source and mode depends on the objective of the study; most surveys are sample surveys, but both must guard against non-sampling errors.
7 Source-Based Questions
(A) 2 marks Which sampling is used in the passage? Why is this survey not a census?
Answer: Random sampling, as households are chosen as if by drawing slips and each has an equal chance. (1)
It is not a census because only selected households are asked, not every household; it is a sample survey. (1)
(B) 2 marks ‘The questionnaire was first tried out in a few villages’: what is this called and what did it achieve? Which agency in the book runs such a survey?
Answer: It is a pilot survey (pre-testing of the questionnaire); it revealed shortcomings of the questions (two confusing ones) and the performance of enumerators. (1)
The NSSO runs such surveys; its 68th round (2011-12) was on consumer expenditure, and its quarterly journal is Sarvekshana. (1)
8 Picture / Cartoon-Based Questions
(A) 1 mark Which sample is the representative sample?
Answer: Sample A (5 kuchha + 5 pucca), as it keeps the population’s half-and-half mix. (1)
(B) 1 mark Why may a conclusion about pucca houses drawn from Sample B be wrong?
Answer: It has only 2 pucca houses (20%) against 50% in the population; the sample is not representative. (1)
(C) 2 marks What kind of sampling is more likely to produce a sample like B? How can a representative sample be obtained?
Answer: Non-random sampling, when the investigator picks houses by convenience or judgement (e.g. nearby kuchha houses). (1)
Use random sampling: make slips for all 40 houses and draw by the lottery method, so that each house has an equal chance. (1)
9 Data / Graph-Based Questions
(A) 1 mark Find the population mean (parameter).
Answer: (20 + 30 + 40 + 50 + 60 + 40) ÷ 6 = 240 ÷ 6 = ₹40 thousand. (1)
(B) 3 marks Find the sampling error for each student and say whose estimate is better and why.
Answer: First student: sample mean = (20 + 30) ÷ 2 = 25; error = 40 − 25 = ₹15 thousand. (1)
Second student: sample mean = (30 + 40 + 50 + 40) ÷ 4 = 160 ÷ 4 = 40; error = 40 − 40 = 0. (1)
The second estimate is better: the sample is larger, and a larger sample reduces sampling error. (1)