A permutation test for nonindependent matched pair data

Seung Ho Kang, H. W. Kim, C. W. Ahn

Research output: Contribution to journalReview article

Abstract

The paired t-test and the Wilcoxon signed-rank test are often conducted to compare two continuous outcomes from paired observations. An assumption underlying these tests is that the responses from pair to pair are mutually independent. However, the assumption is violated in certain applications such as site-specific data in periodontal research. An adjustment to the paired t-test to account for the clustering effect has been well developed. But the adjustment relies on either large sample theory or the assumption that the observations being analyzed follow a normal distribution. In this paper, we propose a permutation test for matched pair clustered data which are valid in small samples. We developed and reviewed software to carry out the proposed test. The proposed test is applied to real-life data.

Original languageEnglish
Pages (from-to)407-411
Number of pages5
JournalDrug Information Journal
Volume35
Issue number2
DOIs
Publication statusPublished - 2001 Jan 1

Fingerprint

Normal Distribution
Normal distribution
Nonparametric Statistics
Cluster Analysis
Software
Research

All Science Journal Classification (ASJC) codes

  • Pharmacology (nursing)
  • Drug guides
  • Public Health, Environmental and Occupational Health
  • Pharmacology (medical)

Cite this

Kang, Seung Ho ; Kim, H. W. ; Ahn, C. W. / A permutation test for nonindependent matched pair data. In: Drug Information Journal. 2001 ; Vol. 35, No. 2. pp. 407-411.
@article{33e972c269774162a7e6673fa4813835,
title = "A permutation test for nonindependent matched pair data",
abstract = "The paired t-test and the Wilcoxon signed-rank test are often conducted to compare two continuous outcomes from paired observations. An assumption underlying these tests is that the responses from pair to pair are mutually independent. However, the assumption is violated in certain applications such as site-specific data in periodontal research. An adjustment to the paired t-test to account for the clustering effect has been well developed. But the adjustment relies on either large sample theory or the assumption that the observations being analyzed follow a normal distribution. In this paper, we propose a permutation test for matched pair clustered data which are valid in small samples. We developed and reviewed software to carry out the proposed test. The proposed test is applied to real-life data.",
author = "Kang, {Seung Ho} and Kim, {H. W.} and Ahn, {C. W.}",
year = "2001",
month = "1",
day = "1",
doi = "10.1177/009286150103500209",
language = "English",
volume = "35",
pages = "407--411",
journal = "Drug Information Journal",
issn = "0092-8615",
publisher = "Drug Information Association",
number = "2",

}

A permutation test for nonindependent matched pair data. / Kang, Seung Ho; Kim, H. W.; Ahn, C. W.

In: Drug Information Journal, Vol. 35, No. 2, 01.01.2001, p. 407-411.

Research output: Contribution to journalReview article

TY - JOUR

T1 - A permutation test for nonindependent matched pair data

AU - Kang, Seung Ho

AU - Kim, H. W.

AU - Ahn, C. W.

PY - 2001/1/1

Y1 - 2001/1/1

N2 - The paired t-test and the Wilcoxon signed-rank test are often conducted to compare two continuous outcomes from paired observations. An assumption underlying these tests is that the responses from pair to pair are mutually independent. However, the assumption is violated in certain applications such as site-specific data in periodontal research. An adjustment to the paired t-test to account for the clustering effect has been well developed. But the adjustment relies on either large sample theory or the assumption that the observations being analyzed follow a normal distribution. In this paper, we propose a permutation test for matched pair clustered data which are valid in small samples. We developed and reviewed software to carry out the proposed test. The proposed test is applied to real-life data.

AB - The paired t-test and the Wilcoxon signed-rank test are often conducted to compare two continuous outcomes from paired observations. An assumption underlying these tests is that the responses from pair to pair are mutually independent. However, the assumption is violated in certain applications such as site-specific data in periodontal research. An adjustment to the paired t-test to account for the clustering effect has been well developed. But the adjustment relies on either large sample theory or the assumption that the observations being analyzed follow a normal distribution. In this paper, we propose a permutation test for matched pair clustered data which are valid in small samples. We developed and reviewed software to carry out the proposed test. The proposed test is applied to real-life data.

UR - http://www.scopus.com/inward/record.url?scp=0034994785&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0034994785&partnerID=8YFLogxK

U2 - 10.1177/009286150103500209

DO - 10.1177/009286150103500209

M3 - Review article

VL - 35

SP - 407

EP - 411

JO - Drug Information Journal

JF - Drug Information Journal

SN - 0092-8615

IS - 2

ER -