• Foundation
  • About 20 min
  • 5 practice questions

Census, sample surveys and methods of sampling

Distinguish a census from a sample survey, define population and representative sample, and explain random (lottery, random number table) and non-random sampling.

If something looks wrong, please tell us.

By the end of this lesson you can

  • Define population (universe), sample and representative sample.
  • Give reasons why most surveys are sample surveys.
  • Select a random sample by the lottery method or a random number table, and explain non-random sampling.

Should we ask everyone, or only some? A survey that covers every element of the population is a census (complete enumeration). A survey that covers a selected part is a sample survey. Most surveys are sample surveys, and this lesson explains why and how samples are chosen.

Census or complete enumeration

In a census, information is obtained from every unit. The Census of India, for example, is a house-to-house enquiry covering all households in the country, collecting demographic data such as birth and death rates, literacy, employment, life expectancy and the size and composition of the population. According to the textbook it is carried out every ten years and its results are published by the Registrar General of India.

Population and sample

Population (or universe): every item that the study is about, so that its findings are meant to hold for all of them. Sample: the part of the population that is actually questioned or measured.

The first task is to identify the population. If surveying all of it is not possible, the researcher selects a representative sample: a sample, usually much smaller than the population, that reflects its features and gives reasonably accurate information about it at a much lower cost and in a shorter time. For example, to estimate the average income in a region, instead of finding every person's income we can find the incomes of a representative sample and use their average as an estimate for the whole region.

Worked example 1: identifying population and sample

Research problem (illustrative)PopulationSample
Opinion of Class 11 students of a made-up school on the new canteen menuAll Class 11 students of that school40 students selected from them
Average yield of rice in a made-up districtAll rice fields in the districtA selection of 150 fields
Cropping pattern in a village of 400 farms, of which 80 are surveyedAll 400 farmsThe 80 farms surveyed (sample size 80)

For the last row, the sample is (80 ÷ 400) × 100 = 20 per cent of the population. If 25 per cent of the surveyed farms grow only cotton, that is 0.25 × 80 = 20 farms in the sample.

Why most surveys are sample surveys

  • A sample gives reasonably reliable and accurate information at lower cost and in shorter time.
  • Because the sample is small, more detailed information can be collected through intensive enquiries.
  • A smaller team of enumerators is needed, which is easier to train and supervise.

Random sampling

In random sampling, units are selected at random so that every individual has an equal chance of being selected. The list of all units from which the sample is drawn is the sampling frame. Ways of drawing a random sample:

  • Lottery method: write the name or number of each unit on identical slips, mix them well and draw the required number one by one.
  • Random number tables: number the units, then read numbers from a published table of random numbers, keeping those that fall within the range and skipping repeats.
  • Computer programmes: today random samples are usually drawn by computer.

Worked example 2: lottery method and counting possible samples

Illustrative: select 3 students out of 8 for a made-up interview panel. Lottery steps: write the 8 names on identical slips, fold them the same way, mix them in a box and draw 3 slips one by one without looking. Each student has the same chance, 3 in 8. How many different samples are possible? The number of ways to choose 3 from 8 is 8 × 7 × 6 ÷ (3 × 2 × 1) = 336 ÷ 6 = 56. Check by another route: choosing 3 to include is the same as choosing 5 to leave out: 8 × 7 × 6 × 5 × 4 ÷ (5 × 4 × 3 × 2 × 1) = 6,720 ÷ 120 = 56. In a random draw, each of these 56 samples is equally likely.

Worked example 3: using a random number table

Illustrative: a frame of 50 households is numbered 01 to 50 and we need 4. Suppose a row of two-digit random numbers (made up for practice) reads: 23, 67, 05, 91, 23, 44, 12, 38. Step 1: keep numbers from 01 to 50: 23, 05, 23, 44, 12, 38. Step 2: skip the repeated 23. Step 3: take the first four distinct numbers: 23, 05, 44, 12. Households 23, 5, 44 and 12 form the sample. 67 and 91 were skipped because no household has those numbers.

Non-random sampling

In non-random sampling, not all units have an equal chance of selection; the investigator's convenience or judgement decides. Choosing the 10 households nearest the road, or the ones known to you, out of 100 is non-random. Such samples are chosen on the basis of judgement, purpose, convenience or quota, and they carry a risk of bias.

Methods of sampling

  • Random sampling Every unit has an equal chance
    • Lottery method
    • Random number tables
    • Computer programmes
  • Non-random sampling Selection depends on the investigator
    • Judgement
    • Purpose
    • Convenience
    • Quota

A population of houses that is half kutcha and half pucca makes the idea of representativeness clear: a sample that is also roughly half and half represents it, while a sample of only pucca houses does not.

Key takeaways: a census covers every unit; a sample survey covers a part. The population is the whole group studied; a representative sample reflects it at lower cost and time. Random sampling gives every unit an equal chance (lottery, random number tables, computers); non-random sampling relies on judgement, purpose, convenience or quota and may be biased.

Check your understanding

  1. 1. A survey that collects information from every unit of the population is called:

    1. a pilot survey
    2. a sample survey
    3. a census or complete enumeration
    4. an exit poll
    Show answer

    Answer: C. Covering every element of the population is the census method, also called complete enumeration.

  2. 2. Illustrative: how many different samples of 2 students can be drawn from 6 students?

    1. 12
    2. 15
    3. 30
    4. 36
    Show answer

    Answer: B. Number of ways = 6 × 5 ÷ (2 × 1) = 30 ÷ 2 = 15. 30 counts each pair twice (A-B and B-A), so it must be halved.

  3. 3. In a random sample:

    1. every unit of the population has an equal chance of selection
    2. only convenient units are chosen
    3. the investigator chooses units he knows
    4. units are chosen by quota
    Show answer

    Answer: A. The defining feature of random sampling is that every unit has an equal chance of being selected; the other three describe non-random methods.

  4. 4. Case: to study the spending habits of a made-up town's 2,000 families, an investigator interviews 100 families living near her own house. This sample is:

    1. random, because 100 is a large number
    2. a census, because it covers a town
    3. a pilot survey
    4. non-random, because convenience decided who was chosen
    Show answer

    Answer: D. Families near her house were chosen for convenience, so the other families had no chance of selection. The size of the sample does not make it random.

  5. 5. Assertion (A): Most surveys are sample surveys. Reason (R): A sample can give reasonably reliable information at lower cost and in shorter time, and allows more intensive enquiry.

    1. Both A and R are true, and R is the correct explanation of A
    2. Both A and R are true, but R is not the correct explanation of A
    3. A is true, but R is false
    4. A is false, but R is true
    Show answer

    Answer: A. Both are true, and R explains A: the cost, time and depth advantages of samples are why most surveys use them.

Privacy · Terms · Refunds · Delivery