A multivariate version of the Benjamini-Hochberg method

JA Ferreira; Stephen Nyangoma

doi:10.1016/j.jmva.2008.02.013

A multivariate version of the Benjamini-Hochberg method

JA Ferreira, Stephen Nyangoma

Cancer Clinical Trials Unit

Research output: Contribution to journal › Article

5 Citations (Scopus)

Abstract

We propose a multivariate method for combining results from independent studies about the same 'large scale' multiple testing problem. The method works asymptotically in the number of hypotheses and consists of applying the Benjamini-Hochberg procedure to the p-values of each study separately by determining the 'individual false discovery rates' which maximize power subject to a restriction on the (global) false discovery rate. We show how to obtain solutions to the associated optimization problem, provide both theoretical and numerical examples, and compare the method with univariate ones. (C) 2008 Elsevier Inc. All rights reserved.

Original language	English
Pages (from-to)	2108-2124
Number of pages	17
Journal	Journal of Multivariate Analysis
Volume	99
Issue number	9
DOIs	https://doi.org/10.1016/j.jmva.2008.02.013
Publication status	Published - 1 Oct 2008

Keywords

Empirical distributions
Multiple testing
Average power
False discovery rate

Access to Document

10.1016/j.jmva.2008.02.013

Statistical Methodology for the Design and Analysis of Protein Mass Spectrometry Studies
Billingham, L., Wei, W. & Johnson, P.
Medical Research Council
1/12/06 → 30/11/09
Project: Research Councils

Cite this

@article{d04a0a58cc0c4af4aaa3d548125cbffc,

title = "A multivariate version of the Benjamini-Hochberg method",

abstract = "We propose a multivariate method for combining results from independent studies about the same 'large scale' multiple testing problem. The method works asymptotically in the number of hypotheses and consists of applying the Benjamini-Hochberg procedure to the p-values of each study separately by determining the 'individual false discovery rates' which maximize power subject to a restriction on the (global) false discovery rate. We show how to obtain solutions to the associated optimization problem, provide both theoretical and numerical examples, and compare the method with univariate ones. (C) 2008 Elsevier Inc. All rights reserved.",

keywords = "Empirical distributions, Multiple testing, Average power, False discovery rate",

author = "JA Ferreira and Stephen Nyangoma",

year = "2008",

month = oct,

day = "1",

doi = "10.1016/j.jmva.2008.02.013",

language = "English",

volume = "99",

pages = "2108--2124",

journal = "Journal of Multivariate Analysis",

issn = "0047-259X",

publisher = "Elsevier",

number = "9",

}

TY - JOUR

T1 - A multivariate version of the Benjamini-Hochberg method

AU - Ferreira, JA

AU - Nyangoma, Stephen

PY - 2008/10/1

Y1 - 2008/10/1

N2 - We propose a multivariate method for combining results from independent studies about the same 'large scale' multiple testing problem. The method works asymptotically in the number of hypotheses and consists of applying the Benjamini-Hochberg procedure to the p-values of each study separately by determining the 'individual false discovery rates' which maximize power subject to a restriction on the (global) false discovery rate. We show how to obtain solutions to the associated optimization problem, provide both theoretical and numerical examples, and compare the method with univariate ones. (C) 2008 Elsevier Inc. All rights reserved.

AB - We propose a multivariate method for combining results from independent studies about the same 'large scale' multiple testing problem. The method works asymptotically in the number of hypotheses and consists of applying the Benjamini-Hochberg procedure to the p-values of each study separately by determining the 'individual false discovery rates' which maximize power subject to a restriction on the (global) false discovery rate. We show how to obtain solutions to the associated optimization problem, provide both theoretical and numerical examples, and compare the method with univariate ones. (C) 2008 Elsevier Inc. All rights reserved.

KW - Empirical distributions

KW - Multiple testing

KW - Average power

KW - False discovery rate

U2 - 10.1016/j.jmva.2008.02.013

DO - 10.1016/j.jmva.2008.02.013

M3 - Article

SN - 0047-259X

VL - 99

SP - 2108

EP - 2124

JO - Journal of Multivariate Analysis

JF - Journal of Multivariate Analysis

IS - 9

ER -

A multivariate version of the Benjamini-Hochberg method

Abstract

Keywords

Access to Document

Fingerprint

Projects

Statistical Methodology for the Design and Analysis of Protein Mass Spectrometry Studies

Cite this