Adjusting O'Brien's test to control type I error for the generalized nonparametric Behrens-Fisher problem

Peng Huang; Barbara C. Tilley; Robert F. Woolson; Stuart Lipsitz

doi:10.1111/j.1541-0420.2005.00322.x

Adjusting O'Brien's test to control type I error for the generalized nonparametric Behrens-Fisher problem

Peng Huang, Barbara C. Tilley, Robert F. Woolson, Stuart Lipsitz

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

39 Scopus citations

Abstract

O'Brien (1984. Biometrics 40, 1079-1087) introduced a simple nonparametric test procedure for testing whether multiple outcomes in one treatment group have consistently larger values than outcomes in the other treatment group. We first explore the theoretical properties of O'Brien's test. We then extend it to the general nonparametric Behrens-Fisher hypothesis problem when no assumption is made regarding the shape of the distributions. We provide conditions when O'Brien's test controls its error probability asymptotically and when it fails. We also provide adjusted tests when the conditions do not hold. Throughout this article, we do not assume that all outcomes are continuous. Simulations are performed to compare the adjusted tests to O'Brien's test. The difference is also illustrated using data from a Parkinson's disease clinical trial.

Original language	English (US)
Pages (from-to)	532-539
Number of pages	8
Journal	Biometrics
Volume	61
Issue number	2
DOIs	https://doi.org/10.1111/j.1541-0420.2005.00322.x
State	Published - Jun 2005
Externally published	Yes

Keywords

Bonferroni
Global statistical test
Multivariate test
Rank test
Rank-sum-type test

ASJC Scopus subject areas

Statistics and Probability
General Biochemistry, Genetics and Molecular Biology
General Immunology and Microbiology
General Agricultural and Biological Sciences
Applied Mathematics

Access to Document

10.1111/j.1541-0420.2005.00322.x

Cite this

@article{64f8a30b7c52435fa6149341c3a196f4,

title = "Adjusting O'Brien's test to control type I error for the generalized nonparametric Behrens-Fisher problem",

abstract = "O'Brien (1984. Biometrics 40, 1079-1087) introduced a simple nonparametric test procedure for testing whether multiple outcomes in one treatment group have consistently larger values than outcomes in the other treatment group. We first explore the theoretical properties of O'Brien's test. We then extend it to the general nonparametric Behrens-Fisher hypothesis problem when no assumption is made regarding the shape of the distributions. We provide conditions when O'Brien's test controls its error probability asymptotically and when it fails. We also provide adjusted tests when the conditions do not hold. Throughout this article, we do not assume that all outcomes are continuous. Simulations are performed to compare the adjusted tests to O'Brien's test. The difference is also illustrated using data from a Parkinson's disease clinical trial.",

keywords = "Bonferroni, Global statistical test, Multivariate test, Rank test, Rank-sum-type test",

author = "Peng Huang and Tilley, {Barbara C.} and Woolson, {Robert F.} and Stuart Lipsitz",

year = "2005",

month = jun,

doi = "10.1111/j.1541-0420.2005.00322.x",

language = "English (US)",

volume = "61",

pages = "532--539",

journal = "Biometrics",

issn = "0006-341X",

publisher = "Wiley-Blackwell",

number = "2",

}

TY - JOUR

T1 - Adjusting O'Brien's test to control type I error for the generalized nonparametric Behrens-Fisher problem

AU - Huang, Peng

AU - Tilley, Barbara C.

AU - Woolson, Robert F.

AU - Lipsitz, Stuart

PY - 2005/6

Y1 - 2005/6

N2 - O'Brien (1984. Biometrics 40, 1079-1087) introduced a simple nonparametric test procedure for testing whether multiple outcomes in one treatment group have consistently larger values than outcomes in the other treatment group. We first explore the theoretical properties of O'Brien's test. We then extend it to the general nonparametric Behrens-Fisher hypothesis problem when no assumption is made regarding the shape of the distributions. We provide conditions when O'Brien's test controls its error probability asymptotically and when it fails. We also provide adjusted tests when the conditions do not hold. Throughout this article, we do not assume that all outcomes are continuous. Simulations are performed to compare the adjusted tests to O'Brien's test. The difference is also illustrated using data from a Parkinson's disease clinical trial.

AB - O'Brien (1984. Biometrics 40, 1079-1087) introduced a simple nonparametric test procedure for testing whether multiple outcomes in one treatment group have consistently larger values than outcomes in the other treatment group. We first explore the theoretical properties of O'Brien's test. We then extend it to the general nonparametric Behrens-Fisher hypothesis problem when no assumption is made regarding the shape of the distributions. We provide conditions when O'Brien's test controls its error probability asymptotically and when it fails. We also provide adjusted tests when the conditions do not hold. Throughout this article, we do not assume that all outcomes are continuous. Simulations are performed to compare the adjusted tests to O'Brien's test. The difference is also illustrated using data from a Parkinson's disease clinical trial.

KW - Bonferroni

KW - Global statistical test

KW - Multivariate test

KW - Rank test

KW - Rank-sum-type test

UR - http://www.scopus.com/inward/record.url?scp=20744444365&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=20744444365&partnerID=8YFLogxK

U2 - 10.1111/j.1541-0420.2005.00322.x

DO - 10.1111/j.1541-0420.2005.00322.x

M3 - Article

C2 - 16011701

AN - SCOPUS:20744444365

SN - 0006-341X

VL - 61

SP - 532

EP - 539

JO - Biometrics

JF - Biometrics

IS - 2

ER -

Adjusting O'Brien's test to control type I error for the generalized nonparametric Behrens-Fisher problem

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this