Evidence-appraisal glossary
Selection bias
Selection bias arises when the people included in a study, or retained in it, differ systematically from the population the results are meant to describe. Because of how participants were chosen or who dropped out, the sample gives a distorted picture that does not generalize accurately.
Also called: sampling bias, self-selection bias.
Selection bias is a distortion introduced by how participants enter or leave a study, so the sample no longer reflects the target population. It can come from the sampling frame (for example, recruiting volunteers who are healthier than average), from differential enrollment of cases and controls, or from loss to follow-up that differs between groups. The result is an association that reflects the selection process rather than a true relationship. When reading a study, ask who was eligible, who actually participated, what the response and dropout rates were, and whether dropout differed by exposure or outcome. A telephone survey conducted only during working hours may undercount employed people, skewing estimates of anything tied to employment. In a trial, if sicker patients leave the treatment arm faster, the remaining treated group can look artificially healthy. The question it lets you ask: are the people in this analysis representative of the group the conclusion claims to describe?
This is a plain-language methodology definition for reading research. It is general education, not medical advice.