Bayes factors based on test statistics

Journal of the Royal Statistical Society: Series B (Statistical Methodology) · 2005 · Volume 67 · Issue 5

DOI: 10.1111/j.1467-9868.2005.00521.x

Abstract

Summary.Traditionally, the use of Bayes factors has required the specification of proper prior distributions on model parameters that are implicit to both null and alternative hypotheses. I describe an approach to defining Bayes factors based on modelling test statistics. Because the distributions of test statistics do not depend on unknown model parameters, this approach eliminates much of the subjectivity that is normally associated with the definition of Bayes factors. For standard test statistics, including theχ2-,F-,t- andz-statistics, the values of Bayes factors that result from this approach have simple, closed form expressions.

Keywords

Bayesian hypothesis tests, Model selection, Posterior model probabilities, Posterior odds, Strength of evidence

Enable JavaScript for citation tools and additional paper interactions.