No matter how carefully a survey is designed, some error is unavoidable when working with a sample instead of the entire population. This final section of Chapter 2, “Collection of Data,” in CBSE Class 11 Statistics for Economics explains the two categories of error every researcher must understand — sampling error and non-sampling error — and introduces the two major agencies behind India’s official statistics: the Census of India and the National Sample Survey Office (NSSO). We close with an exam-ready checklist for the chapter.

Sampling Errors: The Gap Between Sample and Population

The purpose of a sample is to estimate one or more characteristics of the whole population — its parameters. A population’s numerical values have two important characteristics: Central Tendency, measured by the mean, median, or mode, and Dispersion, measured through the standard deviation, mean deviation, or range.

Sampling error refers to the difference between the sample estimate and the true, corresponding population parameter. In other words, it is the gap between the actual value of a characteristic in the entire population and its estimate derived from the sample.

Worked Example

Consider the incomes of 5 farmers in Manipur: ₹500, ₹550, ₹600, ₹650, and ₹700.

  • Population average = (500 + 550 + 600 + 650 + 700) ÷ 5 = 3000 ÷ 5 = 600

Now suppose we select a sample of just two individuals, with incomes of ₹500 and ₹600.

  • Sample average = (500 + 600) ÷ 2 = 1100 ÷ 2 = 550

  • Sampling error = 600 (true value) − 550 (estimate) = 50

The key takeaway: sampling error can be reduced by taking a larger sample. The bigger and more representative your sample, the closer its average tends to move toward the true population value.

Non-Sampling Errors: More Serious, Harder to Fix

Non-sampling errors are considered more serious than sampling errors because a sampling error can be minimised simply by taking a larger sample, while a non-sampling error cannot be reduced this way. Even a full Census, covering the entire population, can still contain non-sampling errors. There are three main types:

1. Sampling Bias

Sampling bias occurs when the sampling plan itself is flawed in a way that certain members of the target population could never possibly be included in the sample, regardless of how the selection is carried out.

2. Non-Response Errors

Non-response occurs when an interviewer is unable to contact a person listed in the sample, or when a selected person refuses to respond. When this happens, the resulting sample observations may no longer be representative of the true population.

3. Errors in Data Acquisition

This type of error arises from recording incorrect responses. For example, if a teacher asks students to measure the length of a table, the measurements may differ due to differences in measuring tapes or carelessness. Similarly, recording mistakes can occur when enumerators transcribe data incorrectly — for instance, writing “13” instead of “31.”

Census of India and NSSO: The Two Key National Agencies

India has several agencies at the national and state level that collect, process, and tabulate statistical data, including the Central Statistics Office (CSO), Registrar General of India (RGI), and the Labour Bureau. Two agencies deserve special attention.

Census of India

The Census of India provides the most complete and continuous demographic record of the country’s population. It has been conducted regularly every ten years since 1881, with the first Census after Independence held in 1951. Census officials collect information on population size, density, sex ratio, literacy, migration, and rural-urban distribution, which is then interpreted and analysed to understand economic and social issues across India.

National Sample Survey Office (NSSO)

The NSS was established by the Government of India to conduct nationwide surveys on socio-economic issues. Unlike the Census, it runs continuous surveys in successive “rounds,” each often focused on a theme — the 60th round (2004) covered morbidity and healthcare, while the 68th round (2011-12) covered consumer expenditure. NSS data is released through reports and its quarterly journal, Sarvekshana, and covers literacy, school enrolment, employment, unemployment, and industrial activity, feeding directly into government planning.

Chapter 2 Exam-Ready Checklist

Before your exam, make sure you can confidently answer these recurring question types from this chapter:

  • Distinguish primary data from secondary data with an original example.

  • Identify what’s wrong with a poorly framed survey question and rewrite it correctly.

  • Compare personal interviews, mailing surveys, and telephone interviews on cost, time, and response rate.

  • Define Census and Sample Survey, and explain when each is appropriate.

  • Explain random versus non-random sampling with the lottery method as an example.

  • Calculate a simple sampling error given population and sample values.

  • List the three types of non-sampling errors and explain why they’re harder to fix than sampling errors.

  • Name the two key national statistical agencies and one distinguishing feature of each.

Ready to Master Statistics for Economics?

From sampling error calculations to identifying non-sampling bias, this is exactly the kind of applied concept that benefits from repeated, varied practice questions. ChampionsPrep offers AI-powered question banks built directly from the NCERT syllabus for CBSE and Maharashtra Board Class XI-XII Commerce students. It’s free to register, and you pay only as you use the platform — no subscriptions, no upfront cost. Start practising Statistics for Economics on ChampionsPrep today. Get started at app.championsprep.in .

Sampling and Non-Sampling Errors: Census of India, NSSO and Exam Tips (Class 11 Ch 2) podcast artwork
Audio LessonClass 11

Sampling and Non-Sampling Errors: Census of India, NSSO and Exam Tips (Class 11 Ch 2)

ChampionsPrep EconomicsEpisode 721:03

Subscribe in any podcast app:

Frequently Asked Questions

What is the difference between sampling error and non-sampling error? +

Sampling error is the difference between a sample estimate and the true population parameter, and it can be reduced by taking a larger sample. Non-sampling error arises from issues like bias, non-response, or recording mistakes, and cannot be reduced simply by increasing sample size.

Can non-sampling errors occur even in a Census? +

Yes. Even though a Census covers the entire population and therefore has no sampling error, it can still suffer from non-sampling errors such as incorrect data recording or non-response from certain households.

What is sampling bias? +

Sampling bias occurs when the sampling plan is designed in such a way that some members of the target population could never possibly be included in the sample, regardless of the selection method used.

How often is the Census of India conducted, and by whom? +

The Census of India is conducted every ten years, regularly since 1881, and the resulting demographic data is collected and published by the Registrar General of India.

What does the NSSO do differently from the Census of India? +

Unlike the Census, which counts the entire population once every ten years, the NSSO conducts continuous nationwide sample surveys in successive rounds, each often focused on a specific socio-economic theme such as healthcare or consumer expenditure.