On the geometric modeling approach to empirical null distribution estimation for empirical Bayes modeling of multiple hypothesis testing

Baolin Wu

doi:10.1016/j.compbiolchem.2012.12.001

On the geometric modeling approach to empirical null distribution estimation for empirical Bayes modeling of multiple hypothesis testing

Baolin Wu

Biostatistics

Research output: Contribution to journal › Article › peer-review

2 Scopus citations

Abstract

We study the geometric modeling approach to estimating the null distribution for the empirical Bayes modeling of multiple hypothesis testing. The commonly used method is a nonparametric approach based on the Poisson regression, which however could be unduly affected by the dependence among test statistics and perform very poorly under strong dependence. In this paper, we explore a finite mixture model based geometric modeling approach to empirical null distribution estimation and multiple hypothesis testing. Through simulations and applications to two public microarray data, we will illustrate its competitive performance.

Original language	English (US)
Pages (from-to)	17-22
Number of pages	6
Journal	Computational Biology and Chemistry
Volume	43
DOIs	https://doi.org/10.1016/j.compbiolchem.2012.12.001
State	Published - 2013

Bibliographical note

Funding Information:
This research was supported in part by NIH grant GM083345 and CA134848 . I would like to thank the anonymous referee for the constructive comments that have improved the presentation of the paper.

Keywords

Empirical Bayes modeling
Empirical null distribution
False discovery rate
Finite mixture model
Multiple hypotheses testing

Publisher link

10.1016/j.compbiolchem.2012.12.001

Find It

Find It at U of M Libraries

Cite this

@article{539fc1e970a04152b82ca807c1dc5b4b,

title = "On the geometric modeling approach to empirical null distribution estimation for empirical Bayes modeling of multiple hypothesis testing",

abstract = "We study the geometric modeling approach to estimating the null distribution for the empirical Bayes modeling of multiple hypothesis testing. The commonly used method is a nonparametric approach based on the Poisson regression, which however could be unduly affected by the dependence among test statistics and perform very poorly under strong dependence. In this paper, we explore a finite mixture model based geometric modeling approach to empirical null distribution estimation and multiple hypothesis testing. Through simulations and applications to two public microarray data, we will illustrate its competitive performance.",

keywords = "Empirical Bayes modeling, Empirical null distribution, False discovery rate, Finite mixture model, Multiple hypotheses testing",

author = "Baolin Wu",

note = "Funding Information: This research was supported in part by NIH grant GM083345 and CA134848 . I would like to thank the anonymous referee for the constructive comments that have improved the presentation of the paper.",

year = "2013",

doi = "10.1016/j.compbiolchem.2012.12.001",

language = "English (US)",

volume = "43",

pages = "17--22",

journal = "Computational Biology and Chemistry",

issn = "1476-9271",

publisher = "Elsevier Limited",

}

TY - JOUR

T1 - On the geometric modeling approach to empirical null distribution estimation for empirical Bayes modeling of multiple hypothesis testing

AU - Wu, Baolin

N1 - Funding Information: This research was supported in part by NIH grant GM083345 and CA134848 . I would like to thank the anonymous referee for the constructive comments that have improved the presentation of the paper.

PY - 2013

Y1 - 2013

N2 - We study the geometric modeling approach to estimating the null distribution for the empirical Bayes modeling of multiple hypothesis testing. The commonly used method is a nonparametric approach based on the Poisson regression, which however could be unduly affected by the dependence among test statistics and perform very poorly under strong dependence. In this paper, we explore a finite mixture model based geometric modeling approach to empirical null distribution estimation and multiple hypothesis testing. Through simulations and applications to two public microarray data, we will illustrate its competitive performance.

AB - We study the geometric modeling approach to estimating the null distribution for the empirical Bayes modeling of multiple hypothesis testing. The commonly used method is a nonparametric approach based on the Poisson regression, which however could be unduly affected by the dependence among test statistics and perform very poorly under strong dependence. In this paper, we explore a finite mixture model based geometric modeling approach to empirical null distribution estimation and multiple hypothesis testing. Through simulations and applications to two public microarray data, we will illustrate its competitive performance.

KW - Empirical Bayes modeling

KW - Empirical null distribution

KW - False discovery rate

KW - Finite mixture model

KW - Multiple hypotheses testing

UR - http://www.scopus.com/inward/record.url?scp=84872349709&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84872349709&partnerID=8YFLogxK

U2 - 10.1016/j.compbiolchem.2012.12.001

DO - 10.1016/j.compbiolchem.2012.12.001

M3 - Article

C2 - 23314152

AN - SCOPUS:84872349709

SN - 1476-9271

VL - 43

SP - 17

EP - 22

JO - Computational Biology and Chemistry

JF - Computational Biology and Chemistry

ER -

On the geometric modeling approach to empirical null distribution estimation for empirical Bayes modeling of multiple hypothesis testing

Abstract

Bibliographical note

Keywords

Publisher link

Find It

Other files and links

Fingerprint

Cite this