A note on permutation tests of significance for multiple regression coefficients

Michael Long; Kenneth Berry; Paul Mielke

doi:10.2466/pr0.100.2.339-345

A note on permutation tests of significance for multiple regression coefficients

Michael Long, Kenneth Berry, Paul Mielke

Social Sciences Department

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

5 Citations (Scopus)

Abstract

In the vast majority of psychological research utilizing multiple regression analysis, asymptotic probability values are reported. This paper demonstrates that asymptotic estimates of standard errors provided by multiple regression are not always accurate. A resampling permutation procedure is used to estimate the standard errors. In some cases the results differ substantially from the traditional least squares regression estimates.

Original language	English
Pages (from-to)	339-345
Journal	Psychological Reports
Volume	100
Issue number	2
DOIs	https://doi.org/10.2466/pr0.100.2.339-345
Publication status	Published - Apr 2007

Access to Document

10.2466/pr0.100.2.339-345

Cite this

@article{bf6c878b14a840649dcce1c38608346d,

title = "A note on permutation tests of significance for multiple regression coefficients",

abstract = "In the vast majority of psychological research utilizing multiple regression analysis, asymptotic probability values are reported. This paper demonstrates that asymptotic estimates of standard errors provided by multiple regression are not always accurate. A resampling permutation procedure is used to estimate the standard errors. In some cases the results differ substantially from the traditional least squares regression estimates.",

author = "Michael Long and Kenneth Berry and Paul Mielke",

year = "2007",

month = apr,

doi = "10.2466/pr0.100.2.339-345",

language = "English",

volume = "100",

pages = "339--345",

journal = "Psychological Reports",

issn = "0033-2941",

publisher = "SAGE",

number = "2",

}

TY - JOUR

T1 - A note on permutation tests of significance for multiple regression coefficients

AU - Long, Michael

AU - Berry, Kenneth

AU - Mielke, Paul

PY - 2007/4

Y1 - 2007/4

N2 - In the vast majority of psychological research utilizing multiple regression analysis, asymptotic probability values are reported. This paper demonstrates that asymptotic estimates of standard errors provided by multiple regression are not always accurate. A resampling permutation procedure is used to estimate the standard errors. In some cases the results differ substantially from the traditional least squares regression estimates.

AB - In the vast majority of psychological research utilizing multiple regression analysis, asymptotic probability values are reported. This paper demonstrates that asymptotic estimates of standard errors provided by multiple regression are not always accurate. A resampling permutation procedure is used to estimate the standard errors. In some cases the results differ substantially from the traditional least squares regression estimates.

U2 - 10.2466/pr0.100.2.339-345

DO - 10.2466/pr0.100.2.339-345

M3 - Article

SN - 0033-2941

VL - 100

SP - 339

EP - 345

JO - Psychological Reports

JF - Psychological Reports

IS - 2

ER -

A note on permutation tests of significance for multiple regression coefficients

Abstract

Access to Document

Fingerprint

Cite this