Bayesian Statistics,Credentialing Examinations,and the Determination of Passing Points

The Bayesian approach to setting passing points presents an attractive alternative to the normative and absolute standard approaches. The Bayesian approach takes into explicit consideration important variables such as loss ratios, well-defined minimum criterion levels, the nature of existing data on candidate competence, and the true level of functioning of a candidate. In this article, the Bayesian approach to setting passing points on credentialing examinations in the health fields is considered in the context of the Normal model. Several theoretical examples are given to demonstrate the mechanics of the Bayesian procedure. The theoretical example is followed by an application of the method to a credentialing examination in one of the allied health professions, in order to determine a ration al passing point.