Sampling
Sampling is the process of selecting cases from a defined population or access route. A good plan connects recruitment to the inference sought. Probability sampling supports design-based population estimation; nonprobability approaches require a defensible inferential basis and explicit assumptions rather than a blanket claim of representativeness.
Who can enter the study, who actually enters, and to whom can its findings reasonably apply?
How it works
- Define the target population, eligibility, sampling unit, and available frame. Explain whether the aim is estimating a population quantity, studying a process under particular conditions, or examining experiences in a selected group.
- Choose recruitment and selection procedures that match that aim. Document invitation routes, selection probabilities when applicable, exclusions, and response patterns; consider groups the frame or recruitment channel cannot reach.
- Analyze using the actual design and any justified adjustment. Describe nonresponse and coverage limitations, state assumptions needed for wider inference, and avoid equating a large sample with an unbiased sample.
Evidence: (Conducting Surveys, n.d.); (Report of the AAPOR Task Force on Non-Probability Sampling, n.d.)
A campus sleep survey
Teaching scenario
Synthetic example: A student team posts a sleep survey in a late-night gaming society chat. Its accessible sample may be useful for piloting questions among society members, but does not automatically estimate sleep problems across the university. The team compares that route with invitations drawn from an enrollment list and asks what happens if invited students with severe sleep difficulties are less likely to respond. A classroom discussion can separate the recruitment problem from the analysis problem without assuming either procedure guarantees truth. No prevalence estimate is invented.
This example is constructed for learning. It does not report an observed research result.
What can you conclude?
Makes the connection between observed cases and intended conclusions explicit and assessable.
Evidence: (Conducting Surveys, n.d.); (Report of the AAPOR Task Force on Non-Probability Sampling, n.d.)
Limits and common mistakes
- A probability sample can still suffer coverage, nonresponse, and measurement problems.
- Nonprobability recruitment can be useful, but generalization depends on the design, assumptions, and available evidence.
A mistake to catch
Confusing random selection into a sample with random assignment to an experimental condition.
Evidence: (Conducting Surveys, n.d.); (Report of the AAPOR Task Force on Non-Probability Sampling, n.d.)
Sources and inspection notes
Links checked October 21, 2026. Inspection scope is stated for each source; an access date is not a publication date.
- Conducting surveys. (n.d.). https://opentextbc.ca/researchmethods/chapter/conducting-surveys/
Sampling; Sampling Bias; nonresponse Original psychology teaching chapter. Use sampling procedures and nonresponse discussion. Do not reproduce its incorrect probability wording about a realized frequentist interval. Opened and checked 21 October 2026.
- Report of the AAPOR task force on non-probability sampling. (n.d.). https://aapor.org/wp-content/uploads/2022/11/NPS_TF_Report_Final_7_revised_FNL_6_22_13.pdf
Executive summary, printed pages 1–5; introduction Official professional-association methods report, 2013. Supports conditional model-based inference, transparency, and fit for purpose, not blanket endorsement of convenience samples. Opened and checked 21 October 2026.
Keep reading
Spielman, R. M., Jenkins, W. J., & Lovett, M. D. (2020). Psychology 2e. OpenStax. https://openstax.org/books/psychology-2e/pages/2-3-analyzing-findings
Nearest related OpenStax Psychology 2e reading. This is a course connection, not evidence for every specialist detail above.
Specialist reading: Conducting surveys. (n.d.). https://opentextbc.ca/researchmethods/chapter/conducting-surveys/
Related methods
Try the methods · Read a study · Explore psychological measures