An adaptive two-sample test for high-dimensional means

Gongjun Xu, Lifeng Lin, Peng Wei, Wei Pan

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

Several two-sample tests for high-dimensional data have been proposed recently, but they are powerful only against certain alternative hypotheses. In practice, since the true alternative hypothesis is unknown, it is unclear how to choose a powerful test. We propose an adaptive test that maintains high power across a wide range of situations and study its asymptotic properties. Its finite-sample performance is compared with that of existing tests. We apply it and other tests to detect possible associations between bipolar disease and a large number of single nucleotide polymorphisms on each chromosome based on data from a genome-wide association study. Numerical studies demonstrate the superior performance and high power of the proposed test across a wide spectrum of applications.

Original languageEnglish (US)
Pages (from-to)609-624
Number of pages16
JournalBiometrika
Volume103
Issue number3
DOIs
StatePublished - Sep 1 2016

Fingerprint

Adaptive Test
Two-sample Test
Genome-Wide Association Study
Chromosomes
Nucleotides
Polymorphism
Single Nucleotide Polymorphism
High-dimensional
Genes
High Power
testing
sampling
Single nucleotide Polymorphism
Alternatives
High-dimensional Data
Asymptotic Properties
Chromosome
Numerical Study
Genome
Choose

Keywords

  • Genome-wide association study
  • Single nucleotide polymorphism
  • Sum-of-powers test

Cite this

An adaptive two-sample test for high-dimensional means. / Xu, Gongjun; Lin, Lifeng; Wei, Peng; Pan, Wei.

In: Biometrika, Vol. 103, No. 3, 01.09.2016, p. 609-624.

Research output: Contribution to journalArticle

Xu, Gongjun ; Lin, Lifeng ; Wei, Peng ; Pan, Wei. / An adaptive two-sample test for high-dimensional means. In: Biometrika. 2016 ; Vol. 103, No. 3. pp. 609-624.
@article{7974b179508840469d74e95b1ef83c7b,
title = "An adaptive two-sample test for high-dimensional means",
abstract = "Several two-sample tests for high-dimensional data have been proposed recently, but they are powerful only against certain alternative hypotheses. In practice, since the true alternative hypothesis is unknown, it is unclear how to choose a powerful test. We propose an adaptive test that maintains high power across a wide range of situations and study its asymptotic properties. Its finite-sample performance is compared with that of existing tests. We apply it and other tests to detect possible associations between bipolar disease and a large number of single nucleotide polymorphisms on each chromosome based on data from a genome-wide association study. Numerical studies demonstrate the superior performance and high power of the proposed test across a wide spectrum of applications.",
keywords = "Genome-wide association study, Single nucleotide polymorphism, Sum-of-powers test",
author = "Gongjun Xu and Lifeng Lin and Peng Wei and Wei Pan",
year = "2016",
month = "9",
day = "1",
doi = "10.1093/biomet/asw029",
language = "English (US)",
volume = "103",
pages = "609--624",
journal = "Biometrika",
issn = "0006-3444",
publisher = "Oxford University Press",
number = "3",

}

TY - JOUR

T1 - An adaptive two-sample test for high-dimensional means

AU - Xu, Gongjun

AU - Lin, Lifeng

AU - Wei, Peng

AU - Pan, Wei

PY - 2016/9/1

Y1 - 2016/9/1

N2 - Several two-sample tests for high-dimensional data have been proposed recently, but they are powerful only against certain alternative hypotheses. In practice, since the true alternative hypothesis is unknown, it is unclear how to choose a powerful test. We propose an adaptive test that maintains high power across a wide range of situations and study its asymptotic properties. Its finite-sample performance is compared with that of existing tests. We apply it and other tests to detect possible associations between bipolar disease and a large number of single nucleotide polymorphisms on each chromosome based on data from a genome-wide association study. Numerical studies demonstrate the superior performance and high power of the proposed test across a wide spectrum of applications.

AB - Several two-sample tests for high-dimensional data have been proposed recently, but they are powerful only against certain alternative hypotheses. In practice, since the true alternative hypothesis is unknown, it is unclear how to choose a powerful test. We propose an adaptive test that maintains high power across a wide range of situations and study its asymptotic properties. Its finite-sample performance is compared with that of existing tests. We apply it and other tests to detect possible associations between bipolar disease and a large number of single nucleotide polymorphisms on each chromosome based on data from a genome-wide association study. Numerical studies demonstrate the superior performance and high power of the proposed test across a wide spectrum of applications.

KW - Genome-wide association study

KW - Single nucleotide polymorphism

KW - Sum-of-powers test

UR - http://www.scopus.com/inward/record.url?scp=84995493912&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84995493912&partnerID=8YFLogxK

U2 - 10.1093/biomet/asw029

DO - 10.1093/biomet/asw029

M3 - Article

C2 - 28804142

AN - SCOPUS:84995493912

VL - 103

SP - 609

EP - 624

JO - Biometrika

JF - Biometrika

SN - 0006-3444

IS - 3

ER -