Self‐Selected Samples
Andrew Rutherford · Wiley StatsRef: Statistics Reference Online · 2014
Abstract The term “Self‐Selected Samples” is explained. The nature of selection with respect to such samples is described, its relation to other sampling techniques is considered briefly and a distinction between strong and weak selection is made. Strong self‐selected samples are not representative of the population of interest and may very likely differ on pertinent factors. Hence, there are serious problems in generalizing inferences from self‐selected samples to their populations. A very brief outline is provided for three statistical approaches to problems with self‐selected samples: the use of covariates, mixture modeling, and selection modeling.