Revision summary
Non-probability sampling gives no known chance of selection. Convenience, purposive, quota, snowball, and theoretical sampling fit pilots, types, hidden groups, and saturation. Gig networks, SHGs, and caste associations are typical Indian uses. Census and NFHS remain the designs for rates. Name the bias; do not sell a quota as a random national fact.
Model answer
Introduction
Non-probability sampling does not give every unit a known chance of selection. It is not a failed census. It is a set of techniques used when a sampling frame is missing, when the population is hidden, or when the aim is theoretical saturation rather than a population estimate.
Body
Convenience and volunteer samples
- The researcher takes those who are at hand: a college class, a clinic queue, or an online form.
- Condition of use: pilot tests, student exercises, and rapid reconnaissance when bias is admitted.
- Example: a first sketch of gig-app riders waiting at a city hub. It cannot stand in for all informal labour in the Census.
Purposive or judgment sampling
- Cases are chosen because they illustrate a type: a successful SHG, a mill town, a mixed-caste panchayat.
- Condition of use: case study and expert selection when the type, not the proportion, is the object.
- Max Weber’s ideal type logic sits here: the case is chosen for theoretical clarity.
Quota sampling
- Interviewers fill cells by sex, age, or caste until a quota is met, without random draws inside the cell.
- Condition of use: rapid opinion work when a frame is costly, as in some market and exit-poll designs.
- Limit: interviewers pick the easiest persons in the quota, so hidden groups stay hidden.
Snowball or chain referral
- One respondent names the next. Networks of migrants, users of a banned substance, or caste-association office-bearers can be reached this way.
- Condition of use: hidden or rare populations with no list. Bias follows the first seeds and the dense core of the network.
- Example: mapping a platform of gig workers through WhatsApp groups, or tracing a caste association’s office network.
Theoretical sampling
- Barney Glaser and Anselm Strauss select the next case to develop a category, and stop at saturation.
- Condition of use: grounded theory and ethnography, not a NFHS-style estimate of anaemia.
- Example: adding a male unpaid-care case after women’s SHG talk has saturated a theme.
When not to use them
- Official rates of literacy, fertility, or vote share need probability designs like the Census and NFHS.
- Mixing a snowball story with a national percentage without warning is a method error.
Flow diagram
flowchart TD NP[Non-probability] --> CV[Convenience] NP --> PU[Purposive] NP --> QU[Quota] NP --> SN[Snowball] NP --> TH[Theoretical saturation] FR[No frame hidden group] --> NP EST[Population estimate] --> PR[Probability Census NFHS]
Conclusion
Convenience, purposive, quota, snowball, and theoretical sampling are legitimate when the frame is absent, the group is hidden, or the aim is a type. They are the wrong tools for population totals. State the condition, show the bias, and do not dress a chain of names as a Census.
Quick related
Students also ask
-
Discuss social mobility in open and closed system.
Next question in the 2022 paper (Q2). View answer →
-
Is non-probability unscientific?
It is unscientific as a pretence of random inference. It is scientific as a designed way to reach types and hidden groups.
-
Can snowballing study caste?
It can map an association’s network. It cannot give the caste composition of India; that needs a frame such as the Census.
PYQ trend
When UPSC asked this
Related PYQs from other years, newest first. Open a question to read it.
-
2025 · Q3(c) · Sociology GS 1 · 10 marks
What is hypothesis? Critically evaluate the significance of hypothesis in social research -
2025 · Q7(a) · Sociology GS 1 · 20 marks
What is sampling in the context of social research? Discuss different forms of sampling with their relative advantages and disadvantages -
2023 · Q2(c) · Sociology GS 1 · 10 marks
What are variables? How do they facilitate research? -
2021 · Q3(a) · Sociology GS 1 · 20 marks
How do qualitative and quantitative methods supplement each other in sociological enquiry? -
2020 · Q5(b) · Sociology GS 1 · 10 marks
Discuss the importance and sources of hypothesis in social research. -
2018 · Q5(d) · Sociology GS 1 · 10 marks
Distinguish between qualitative techniques of data collection with suitable examples from Indian society. -
2017 · Q3(c) · Sociology GS 1 · 10 marks
Examine epistemological foundation of qualitative methods of social research -
2017 · Q4(c) · Sociology GS 1 · 10 marks
How can one resolve the issue of reliability and validity in the context of sociological research on inequality ?
More from this paper
Q1(a) · UPSC Mains 2022 · Sociology GS 1 · 10 marks
Delimit the scope of sociology in relation to other social sciences.
Sociology
Sociology studies patterned relations among groups and institutions as a whole. Comte, Durkheim, Weber, and Marx named that object in different ways. Economics, political science, psychology, history, and anthropology cut the same life along one axis. Census and NFHS already show large-scale social structure. The limit is complementary science, not a takeover of every neighbouring field.
Q1(b) · UPSC Mains 2022 · Sociology GS 1 · 10 marks
How does a researcher achieve objectivity in interpretative research?
Sociology as Science
Interpretative research studies meaning, not only counts. Weber kept value-relevance in problem choice and demanded value-discipline in proof. Harding’s strong objectivity names the researcher’s location. Geertz, prolonged fieldwork, triangulation, and respondent checks test the reading. Empathy without evidence is not objectivity.
Q1(c) · UPSC Mains 2022 · Sociology GS 1 · 10 marks
The difference between information and data in social science is subtle. Comment.
Social Change in Modern Society
Information is a report; data are information organised for a research question. Durkheim turned official suicide counts into sociological data by classification. Blumer warned that grids can freeze living meanings. Census and NFHS are public information until a defined indicator is built. Numbers alone do not make data.
Toppers' copies
Toppers' copies for this question will be uploaded soon.