Bayesian Decision Theory for Multiple Comparisons
Educational Testing Service
A loss function related to the directional false discovery rate (DFDR) criterion for evaluating multiple comparisons procedures is introduced. The Bayes decision rule for this loss is obtained. When used with a vague prior, this Bayes rule is shown to be very similar to the sampling theory procedure introduced by Benjamini and Hochberg to control the FDR. This provides a new perspective on the properties of FDR-controlling procedures.