Distribution-free confidence intervals for a parameter of Wilcoxon-Mann-Whitney type for ordered categories and progressive censoring

M. Halperin; M. I. Hamdy; P. F. Thall

doi:10.2307/2531493

Distribution-free confidence intervals for a parameter of Wilcoxon-Mann-Whitney type for ordered categories and progressive censoring

M. Halperin, M. I. Hamdy, P. F. Thall

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

29 Scopus citations

Abstract

Halperin, Gilbert, and Lachin (1987, Biometrics 43, 71-80) obtain confidence intervals for Pr(X < V) based on the two-sample Wilcoxon statistic for continuous data. Their approach is applied here to ordered categorical data and right-censored continuous data, using the generalization ζ = Pr(X < Y) + 1/2 Pr(X = Y) to account for ties. Deviations from nominal coverage probability for various sample sizes and values of ζ are obtained via simulation of either three or six ordered categories based on underlying Poisson or exponential distributions. The simulation results indicate that the proposed method performs quite well, and it is apparently superior to the approach of Hochberg (1981, Communications in Statistics - Theory and Methods A10, 1719-1732) for values of ζ far from 1/2 .

Original language	English (US)
Pages (from-to)	509-521
Number of pages	13
Journal	Biometrics
Volume	45
Issue number	2
DOIs	https://doi.org/10.2307/2531493
State	Published - 1989
Externally published	Yes

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

10.2307/2531493

Cite this

@article{2d62d7aea2a8479d8d605f46f0d3501c,

title = "Distribution-free confidence intervals for a parameter of Wilcoxon-Mann-Whitney type for ordered categories and progressive censoring",

abstract = "Halperin, Gilbert, and Lachin (1987, Biometrics 43, 71-80) obtain confidence intervals for Pr(X < V) based on the two-sample Wilcoxon statistic for continuous data. Their approach is applied here to ordered categorical data and right-censored continuous data, using the generalization ζ = Pr(X < Y) + 1/2 Pr(X = Y) to account for ties. Deviations from nominal coverage probability for various sample sizes and values of ζ are obtained via simulation of either three or six ordered categories based on underlying Poisson or exponential distributions. The simulation results indicate that the proposed method performs quite well, and it is apparently superior to the approach of Hochberg (1981, Communications in Statistics - Theory and Methods A10, 1719-1732) for values of ζ far from 1/2 .",

author = "M. Halperin and Hamdy, {M. I.} and Thall, {P. F.}",

year = "1989",

doi = "10.2307/2531493",

language = "English (US)",

volume = "45",

pages = "509--521",

journal = "Biometrics",

issn = "0006-341X",

publisher = "Wiley-Blackwell",

number = "2",

}

TY - JOUR

T1 - Distribution-free confidence intervals for a parameter of Wilcoxon-Mann-Whitney type for ordered categories and progressive censoring

AU - Halperin, M.

AU - Hamdy, M. I.

AU - Thall, P. F.

PY - 1989

Y1 - 1989

N2 - Halperin, Gilbert, and Lachin (1987, Biometrics 43, 71-80) obtain confidence intervals for Pr(X < V) based on the two-sample Wilcoxon statistic for continuous data. Their approach is applied here to ordered categorical data and right-censored continuous data, using the generalization ζ = Pr(X < Y) + 1/2 Pr(X = Y) to account for ties. Deviations from nominal coverage probability for various sample sizes and values of ζ are obtained via simulation of either three or six ordered categories based on underlying Poisson or exponential distributions. The simulation results indicate that the proposed method performs quite well, and it is apparently superior to the approach of Hochberg (1981, Communications in Statistics - Theory and Methods A10, 1719-1732) for values of ζ far from 1/2 .

AB - Halperin, Gilbert, and Lachin (1987, Biometrics 43, 71-80) obtain confidence intervals for Pr(X < V) based on the two-sample Wilcoxon statistic for continuous data. Their approach is applied here to ordered categorical data and right-censored continuous data, using the generalization ζ = Pr(X < Y) + 1/2 Pr(X = Y) to account for ties. Deviations from nominal coverage probability for various sample sizes and values of ζ are obtained via simulation of either three or six ordered categories based on underlying Poisson or exponential distributions. The simulation results indicate that the proposed method performs quite well, and it is apparently superior to the approach of Hochberg (1981, Communications in Statistics - Theory and Methods A10, 1719-1732) for values of ζ far from 1/2 .

UR - http://www.scopus.com/inward/record.url?scp=0024405165&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0024405165&partnerID=8YFLogxK

U2 - 10.2307/2531493

DO - 10.2307/2531493

M3 - Article

C2 - 2765635

AN - SCOPUS:0024405165

SN - 0006-341X

VL - 45

SP - 509

EP - 521

JO - Biometrics

JF - Biometrics

IS - 2

ER -

Distribution-free confidence intervals for a parameter of Wilcoxon-Mann-Whitney type for ordered categories and progressive censoring

Abstract

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this