Optimal weighting for false discovery rate control

Abstract

How to weigh the Benjamini-Hochberg procedure? In the context of multiple hypothesis testing, we propose a new step-wise procedure that controls the false discovery rate (FDR) and we prove it to be more powerful than any weighted Benjamini-Hochberg procedure. Both finite-sample and asymptotic results are presented. Moreover, we illustrate good performance of our procedure in simulations and a genomics application. This work is particularly useful in the case of heterogeneous $p$-value distributions.

References in corpus (3)

• An adaptive step-down procedure with proven FDR control under independence
• On the false discovery rate and an asymptotically optimal rejection curve
• Two simple sufficient conditions for FDR control