Models proposed by Cleary, Thorndike, Cole, Einhorn and Bass, and Darlington for analyzing bias in the use of tests in a selection strategy are surveyed. Six additional models for test bias are also introduced. The purpose is to describe, compare, contrast, and evaluate these models while, at the same time, extracting such useful ideas as may be found in these approaches. Several of these models are judged to contain logical contradictions because of their use of the wrong conditional probability within the context of the probabilistic structure. In the final section of the paper, these models are shown to have highly objectionable practical implications. Two of the models studied are based on the correct conditional probability, and these are noted to be special cases of a more general and more useful model. (Author/RC)