Sample Size Calculation for Rank Tests Comparing K Survival Distributions

Sin Ho Jung, Siu Hui

Research output: Contribution to journalArticle

14 Citations (Scopus)

Abstract

Rank tests, such as logrank or Wilcoxon rank sum tests, have been popularly used to compare survival distributions of two or more groups in the presence of right censoring. However, there has been little research on sample size calculation methods for rank tests to compare more than two groups. An existing method is based on a crude approximation, which tends to underestimate sample size, i.e., the calculated sample size has lower power than projected. In this paper we propose an asymptotically correct method and an approximate method for sample size calculation. The proposed methods are compared to other methods through simulation studies.

Original languageEnglish (US)
Pages (from-to)361-373
Number of pages13
JournalLifetime data analysis
Volume8
Issue number4
DOIs
StatePublished - Dec 1 2002

Fingerprint

Sample Size Calculation
Survival Distribution
Rank Test
Sample Size
Nonparametric Statistics
Wilcoxon rank-sum test
Right Censoring
Simulation Study
Tend
Approximation
Research

Keywords

  • Accrual period
  • Follow-up period
  • Logrank test
  • Noncentral χ test
  • Wilcoxon test

ASJC Scopus subject areas

  • Applied Mathematics
  • Medicine(all)

Cite this

Sample Size Calculation for Rank Tests Comparing K Survival Distributions. / Jung, Sin Ho; Hui, Siu.

In: Lifetime data analysis, Vol. 8, No. 4, 01.12.2002, p. 361-373.

Research output: Contribution to journalArticle

@article{53f9e5b1efa84409abbed09f623ca132,
title = "Sample Size Calculation for Rank Tests Comparing K Survival Distributions",
abstract = "Rank tests, such as logrank or Wilcoxon rank sum tests, have been popularly used to compare survival distributions of two or more groups in the presence of right censoring. However, there has been little research on sample size calculation methods for rank tests to compare more than two groups. An existing method is based on a crude approximation, which tends to underestimate sample size, i.e., the calculated sample size has lower power than projected. In this paper we propose an asymptotically correct method and an approximate method for sample size calculation. The proposed methods are compared to other methods through simulation studies.",
keywords = "Accrual period, Follow-up period, Logrank test, Noncentral χ test, Wilcoxon test",
author = "Jung, {Sin Ho} and Siu Hui",
year = "2002",
month = "12",
day = "1",
doi = "10.1023/A:1020518905233",
language = "English (US)",
volume = "8",
pages = "361--373",
journal = "Lifetime Data Analysis",
issn = "1380-7870",
publisher = "Springer Netherlands",
number = "4",

}

TY - JOUR

T1 - Sample Size Calculation for Rank Tests Comparing K Survival Distributions

AU - Jung, Sin Ho

AU - Hui, Siu

PY - 2002/12/1

Y1 - 2002/12/1

N2 - Rank tests, such as logrank or Wilcoxon rank sum tests, have been popularly used to compare survival distributions of two or more groups in the presence of right censoring. However, there has been little research on sample size calculation methods for rank tests to compare more than two groups. An existing method is based on a crude approximation, which tends to underestimate sample size, i.e., the calculated sample size has lower power than projected. In this paper we propose an asymptotically correct method and an approximate method for sample size calculation. The proposed methods are compared to other methods through simulation studies.

AB - Rank tests, such as logrank or Wilcoxon rank sum tests, have been popularly used to compare survival distributions of two or more groups in the presence of right censoring. However, there has been little research on sample size calculation methods for rank tests to compare more than two groups. An existing method is based on a crude approximation, which tends to underestimate sample size, i.e., the calculated sample size has lower power than projected. In this paper we propose an asymptotically correct method and an approximate method for sample size calculation. The proposed methods are compared to other methods through simulation studies.

KW - Accrual period

KW - Follow-up period

KW - Logrank test

KW - Noncentral χ test

KW - Wilcoxon test

UR - http://www.scopus.com/inward/record.url?scp=0036884927&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0036884927&partnerID=8YFLogxK

U2 - 10.1023/A:1020518905233

DO - 10.1023/A:1020518905233

M3 - Article

C2 - 12471945

AN - SCOPUS:0036884927

VL - 8

SP - 361

EP - 373

JO - Lifetime Data Analysis

JF - Lifetime Data Analysis

SN - 1380-7870

IS - 4

ER -