Optimal weighting for false discovery rate control

被引：41

作者：

Roquain, Etienne ^{[1
]}

van de Wiel, Mark A. ^{[2
]}

机构：

[1] Univ Paris 06, LPMA, F-75252 Paris 05, France

[2] Vrije Univ Amsterdam, Med Ctr, NL-1007 MB Amsterdam, Netherlands

来源：

ELECTRONIC JOURNAL OF STATISTICS | 2009年 / 3卷

关键词：

False discovery rate; multiple testing; p-value weighting; power maximization; DEPENDENCE;

D O I：

10.1214/09-EJS430

中图分类号：

O21 [概率论与数理统计]; C8 [统计学];

学科分类号：

020208 ; 070103 ; 0714 ;

摘要：

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.

引用

页码：678 / 711

页数：34

共 27 条

[1]

Benjamini Y, 2001, ANN STAT, V29, P1165

[2] CONTROLLING THE FALSE DISCOVERY RATE - A PRACTICAL AND POWERFUL APPROACH TO MULTIPLE TESTING [J].