Sampling methods, bias and random selection

Learning objectives

Distinguish a census, an observational study and an experiment, classify an observational study as prospective, retrospective or a sample survey, and explain how a confounding variable limits what an observational study can show

Describe how to select a simple random sample, a stratified random sample, a cluster sample and a systematic random sample, with or without replacement, giving a procedure another person could follow exactly

Identify the sampling method used in a described study, and justify the choice of method for a given investigative question, for example stratifying to reduce variability or clustering to reduce cost

Identify voluntary response bias, undercoverage, non-response bias and response bias, including bias caused by question wording or by self-reported answers, and state the direction in which each is likely to push an estimate

Explain why a convenience sample or a voluntary response sample is biased, and why a larger sample reduces variability but cannot remove bias

Justify how far the results of a study can be generalized: to the whole population when the sample was selected at random, and otherwise only to individuals like those studied