On the first-order Rao-Scott correction of the Umesh-Loughin-Scherer statistic

Christopher R. Bilder; Thomas M. Loughin

doi:10.1111/j.0006-341X.2001.01253.x

On the first-order Rao-Scott correction of the Umesh-Loughin-Scherer statistic

Christopher R. Bilder, Thomas M. Loughin

Research output: Contribution to journal › Short survey › peer-review

8 Scopus citations

Abstract

Decady and Thomas (2000, Biometrics 56, 893-896) propose a first-order corrected UmeshLoughin-Scherer statistic to test for association in an r x c contingency table with multiple column responses. Agresti and Liu (1999, Biometrics 55, 936-943) point out that such statistics are not invariant to the arbitrary designation of a zero or one to a positive response. This paper shows that, in addition, the proposed testing procedure does not hold the correct size when there are strong pairwise associations between responses.

Original language	English (US)
Pages (from-to)	1253-1255
Number of pages	3
Journal	Biometrics
Volume	57
Issue number	4
DOIs	https://doi.org/10.1111/j.0006-341X.2001.01253.x
State	Published - 2001
Externally published	Yes

Keywords

Chi-square test
Modified Pearson statistic
Multiple marginal independence
Multiple response
Pick any data

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.0006-341X.2001.01253.x

Cite this

@article{720167b617994da68f422b18adf96ee1,

title = "On the first-order Rao-Scott correction of the Umesh-Loughin-Scherer statistic",

abstract = "Decady and Thomas (2000, Biometrics 56, 893-896) propose a first-order corrected UmeshLoughin-Scherer statistic to test for association in an r x c contingency table with multiple column responses. Agresti and Liu (1999, Biometrics 55, 936-943) point out that such statistics are not invariant to the arbitrary designation of a zero or one to a positive response. This paper shows that, in addition, the proposed testing procedure does not hold the correct size when there are strong pairwise associations between responses.",

keywords = "Chi-square test, Modified Pearson statistic, Multiple marginal independence, Multiple response, Pick any data",

author = "Bilder, {Christopher R.} and Loughin, {Thomas M.}",

year = "2001",

doi = "10.1111/j.0006-341X.2001.01253.x",

language = "English (US)",

volume = "57",

pages = "1253--1255",

journal = "Biometrics",

issn = "0006-341X",

publisher = "Oxford University Press",

number = "4",

}

TY - JOUR

T1 - On the first-order Rao-Scott correction of the Umesh-Loughin-Scherer statistic

AU - Bilder, Christopher R.

AU - Loughin, Thomas M.

PY - 2001

Y1 - 2001

N2 - Decady and Thomas (2000, Biometrics 56, 893-896) propose a first-order corrected UmeshLoughin-Scherer statistic to test for association in an r x c contingency table with multiple column responses. Agresti and Liu (1999, Biometrics 55, 936-943) point out that such statistics are not invariant to the arbitrary designation of a zero or one to a positive response. This paper shows that, in addition, the proposed testing procedure does not hold the correct size when there are strong pairwise associations between responses.

AB - Decady and Thomas (2000, Biometrics 56, 893-896) propose a first-order corrected UmeshLoughin-Scherer statistic to test for association in an r x c contingency table with multiple column responses. Agresti and Liu (1999, Biometrics 55, 936-943) point out that such statistics are not invariant to the arbitrary designation of a zero or one to a positive response. This paper shows that, in addition, the proposed testing procedure does not hold the correct size when there are strong pairwise associations between responses.

KW - Chi-square test

KW - Modified Pearson statistic

KW - Multiple marginal independence

KW - Multiple response

KW - Pick any data

UR - http://www.scopus.com/inward/record.url?scp=0035192192&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0035192192&partnerID=8YFLogxK

U2 - 10.1111/j.0006-341X.2001.01253.x

DO - 10.1111/j.0006-341X.2001.01253.x

M3 - Short survey

C2 - 11764268

AN - SCOPUS:0035192192

SN - 0006-341X

VL - 57

SP - 1253

EP - 1255

JO - Biometrics

JF - Biometrics

IS - 4

ER -

On the first-order Rao-Scott correction of the Umesh-Loughin-Scherer statistic

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this