Colloquy: Should familywise alpha be adjusted? Against familywise alpha adjustment

Daniel J. O'Keefe

doi:10.1093/hcr/29.3.431

Colloquy: Should familywise alpha be adjusted? Against familywise alpha adjustment

Daniel J. O'Keefe^*

^*Corresponding author for this work

Communication Studies

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

135 Scopus citations

Abstract

Type I error is a risk undertaken whenever significance tests are conducted, and the chances of committing a Type I error increase as the number of significance tests increases. But adjusting the alpha level because of the number of tests conducted in a given study has no principled basis, commits one to absurd beliefs and practices, and reduces statistical power. The practice of requiring or employing such adjustments should be abandoned.

Original language	English (US)
Pages (from-to)	431-447
Number of pages	17
Journal	Human Communication Research
Volume	29
Issue number	3
DOIs	https://doi.org/10.1093/hcr/29.3.431
State	Published - Jul 2003

ASJC Scopus subject areas

Communication
Developmental and Educational Psychology
Anthropology
Linguistics and Language

Access to Document

10.1093/hcr/29.3.431

Cite this

@article{265110c5b4fc4b4890371157ffd3fceb,

title = "Colloquy: Should familywise alpha be adjusted? Against familywise alpha adjustment",

abstract = "Type I error is a risk undertaken whenever significance tests are conducted, and the chances of committing a Type I error increase as the number of significance tests increases. But adjusting the alpha level because of the number of tests conducted in a given study has no principled basis, commits one to absurd beliefs and practices, and reduces statistical power. The practice of requiring or employing such adjustments should be abandoned.",

author = "O'Keefe, {Daniel J.}",

year = "2003",

month = jul,

doi = "10.1093/hcr/29.3.431",

language = "English (US)",

volume = "29",

pages = "431--447",

journal = "Human Communication Research",

issn = "0360-3989",

publisher = "Wiley-Blackwell",

number = "3",

}

TY - JOUR

T1 - Colloquy

T2 - Should familywise alpha be adjusted? Against familywise alpha adjustment

AU - O'Keefe, Daniel J.

PY - 2003/7

Y1 - 2003/7

N2 - Type I error is a risk undertaken whenever significance tests are conducted, and the chances of committing a Type I error increase as the number of significance tests increases. But adjusting the alpha level because of the number of tests conducted in a given study has no principled basis, commits one to absurd beliefs and practices, and reduces statistical power. The practice of requiring or employing such adjustments should be abandoned.

AB - Type I error is a risk undertaken whenever significance tests are conducted, and the chances of committing a Type I error increase as the number of significance tests increases. But adjusting the alpha level because of the number of tests conducted in a given study has no principled basis, commits one to absurd beliefs and practices, and reduces statistical power. The practice of requiring or employing such adjustments should be abandoned.

UR - http://www.scopus.com/inward/record.url?scp=0041823630&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0041823630&partnerID=8YFLogxK

U2 - 10.1093/hcr/29.3.431

DO - 10.1093/hcr/29.3.431

M3 - Article

AN - SCOPUS:0041823630

SN - 0360-3989

VL - 29

SP - 431

EP - 447

JO - Human Communication Research

JF - Human Communication Research

IS - 3

ER -

Colloquy: Should familywise alpha be adjusted? Against familywise alpha adjustment

Abstract

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this