Optimal weighting for false discovery rate control
Statistics Theory
2009-07-13 v3 Statistics Theory
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 -value distributions.
Keywords
Cite
@article{arxiv.0807.4081,
title = {Optimal weighting for false discovery rate control},
author = {Etienne Roquain and Mark Van De Wiel},
journal= {arXiv preprint arXiv:0807.4081},
year = {2009}
}