Sampling Methods Guide
Who or what you study — and how you select them — shapes what your findings can and can't claim. This guide covers the main sampling approaches and how to choose and justify one.
Probability Sampling
In probability sampling, every member of your population has a known, non-zero chance of being selected, which supports stronger claims about generalising findings to the wider population.
| Method | How It Works |
|---|---|
| Simple random sampling | Every individual has an equal chance of selection, typically via random number generation |
| Stratified sampling | Population is divided into subgroups (strata), then randomly sampled within each |
| Systematic sampling | Selecting every nth individual from a list after a random starting point |
| Cluster sampling | Randomly selecting whole groups or clusters, rather than individuals, from the population |
Non-Probability Sampling
In non-probability sampling, selection isn't random, and not every member of the population has a known chance of inclusion. This is extremely common — and entirely acceptable — in student dissertations, given practical access constraints.
| Method | How It Works |
|---|---|
| Convenience sampling | Selecting participants who are easiest to reach or most readily available |
| Purposive sampling | Deliberately selecting participants who meet specific criteria relevant to the research question |
| Snowball sampling | Existing participants refer other potential participants, useful for hard-to-reach populations |
| Quota sampling | Selecting a set number of participants from defined subgroups, without random selection within them |
Choosing a Sample Size
For quantitative research, sample size is often guided by statistical power calculations, the number of variables in your planned analysis, or established rules of thumb for specific tests.
For qualitative research, sample size is typically guided by the concept of data saturation — the point at which additional interviews or data stop generating new themes — rather than a fixed target number.
Justifying Your Sampling Choice
- State clearly who or what your population is.
- Explain why your chosen sampling method fits your research questions and constraints.
- Acknowledge the limitations of your approach honestly, particularly for non-probability samples.
- Justify your sample size against your specific analysis plan, not an arbitrary number.
Key Takeaways
- Probability sampling supports stronger generalisation; non-probability sampling is common and valid in student research
- Qualitative sample size is usually guided by data saturation, not a fixed number
- Always justify your sampling choice against your specific research questions and honestly acknowledge its limitations
Sampling Methods Guide FAQs
Yes, it's widely used and accepted, provided its limitations — such as reduced generalisability — are acknowledged clearly in your methodology.
There's no fixed number — most qualitative dissertations use somewhere between 8 and 20 participants, guided by when new themes stop emerging (data saturation), though this varies by approach and scope.
This is a common real-world constraint — a smaller, well-justified sample with honestly acknowledged limitations is generally more defensible than overstating your reach.