The determination of sample sizes in the comparison of two multinomial proportions from ordered categories

Myoung Keun Lee; Hae Hiang Song; Seung Ho Kang; Chul W. Ahn

doi:10.1002/1521-4036(200206)44:4<395::AID-BIMJ395>3.0.CO;2-D

The determination of sample sizes in the comparison of two multinomial proportions from ordered categories

Myoung Keun Lee, Hae Hiang Song, Seung Ho Kang, Chul W. Ahn

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

8 Scopus citations

Abstract

We consider sample size determination for ordered categorical data when the alternative assumption is the proportional odds model. In this paper the sample size formula proposed by WHITEHEAD (Statistics in Medicine, 12, 2257-2271, 1993) is compared with the methods based on exact and asymptotic linear rank tests with Wilcoxon and trend scores. We show that Whitehead's formula, which is based on a normal approximation, works well when the sample size is moderate to large but recommend the exact method with Wilcoxon scores for small sample sizes. The consequences of misspecification in models are also investigated.

Original language	English (US)
Pages (from-to)	395-409
Number of pages	15
Journal	Biometrical Journal
Volume	44
Issue number	4
DOIs	https://doi.org/10.1002/1521-4036(200206)44:4<395::AID-BIMJ395>3.0.CO;2-D
State	Published - 2002

Keywords

Exact power
Ordinal data
Proportional odds model
Trend scores
Wilcoxon scores

ASJC Scopus subject areas

Statistics and Probability
Statistics, Probability and Uncertainty

Access to Document

10.1002/1521-4036(200206)44:4<395::AID-BIMJ395>3.0.CO;2-D

Cite this

@article{165ea27f877a4088a20eab2b89b84cd7,

title = "The determination of sample sizes in the comparison of two multinomial proportions from ordered categories",

abstract = "We consider sample size determination for ordered categorical data when the alternative assumption is the proportional odds model. In this paper the sample size formula proposed by WHITEHEAD (Statistics in Medicine, 12, 2257-2271, 1993) is compared with the methods based on exact and asymptotic linear rank tests with Wilcoxon and trend scores. We show that Whitehead's formula, which is based on a normal approximation, works well when the sample size is moderate to large but recommend the exact method with Wilcoxon scores for small sample sizes. The consequences of misspecification in models are also investigated.",

keywords = "Exact power, Ordinal data, Proportional odds model, Trend scores, Wilcoxon scores",

author = "Lee, {Myoung Keun} and Song, {Hae Hiang} and Kang, {Seung Ho} and Ahn, {Chul W.}",

year = "2002",

doi = "10.1002/1521-4036(200206)44:4<395::AID-BIMJ395>3.0.CO;2-D",

language = "English (US)",

volume = "44",

pages = "395--409",

journal = "Biometrical Journal",

issn = "0323-3847",

publisher = "Wiley-VCH Verlag",

number = "4",

}

TY - JOUR

T1 - The determination of sample sizes in the comparison of two multinomial proportions from ordered categories

AU - Lee, Myoung Keun

AU - Song, Hae Hiang

AU - Kang, Seung Ho

AU - Ahn, Chul W.

PY - 2002

Y1 - 2002

N2 - We consider sample size determination for ordered categorical data when the alternative assumption is the proportional odds model. In this paper the sample size formula proposed by WHITEHEAD (Statistics in Medicine, 12, 2257-2271, 1993) is compared with the methods based on exact and asymptotic linear rank tests with Wilcoxon and trend scores. We show that Whitehead's formula, which is based on a normal approximation, works well when the sample size is moderate to large but recommend the exact method with Wilcoxon scores for small sample sizes. The consequences of misspecification in models are also investigated.

AB - We consider sample size determination for ordered categorical data when the alternative assumption is the proportional odds model. In this paper the sample size formula proposed by WHITEHEAD (Statistics in Medicine, 12, 2257-2271, 1993) is compared with the methods based on exact and asymptotic linear rank tests with Wilcoxon and trend scores. We show that Whitehead's formula, which is based on a normal approximation, works well when the sample size is moderate to large but recommend the exact method with Wilcoxon scores for small sample sizes. The consequences of misspecification in models are also investigated.

KW - Exact power

KW - Ordinal data

KW - Proportional odds model

KW - Trend scores

KW - Wilcoxon scores

UR - http://www.scopus.com/inward/record.url?scp=0035998046&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0035998046&partnerID=8YFLogxK

U2 - 10.1002/1521-4036(200206)44:4<395::AID-BIMJ395>3.0.CO;2-D

DO - 10.1002/1521-4036(200206)44:4<395::AID-BIMJ395>3.0.CO;2-D

M3 - Article

AN - SCOPUS:0035998046

SN - 0323-3847

VL - 44

SP - 395

EP - 409

JO - Biometrical Journal

JF - Biometrical Journal

IS - 4

ER -

The determination of sample sizes in the comparison of two multinomial proportions from ordered categories

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this