Asymptotic powers for matched trend tests and robust matched trend tests in case-control genetic association studies

Yong Zang, Wing Kam Fung, Gang Zheng

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

The matched trend test (MTT), developed using a conditional logistic regression, has been proposed to test for association in matched case-control studies to control the bias of known confounding effects and reduce the potential impact of population stratification. The MTT requires a known genetic model. When the genetic model is unknown, a Monte Carlo robust test, MAX, has been proposed for the analysis of matched case-control studies. The MAX statistic takes the maximum of three MTTs optimal for three common genetic models. We derive the asymptotic power for MTTs and robust tests. In particular, we derive the asymptotic p-value for MAX. Using these analytical results, we conduct simulation studies to compare the performance of MAX and the two-degree-of-freedom Chi-square test for matched case-control studies, where the latter is implemented in most computing software. Our simulation results show that MAX is always asymptotically more powerful than the two-degree-of-freedom Chi-square test under common genetic models. Our results provide guidelines for the analysis of genetic association using matched case-control data. An illustration of our results to a real matched pair case-control etiologic study of sarcoidosis is given.

Original languageEnglish (US)
Pages (from-to)65-77
Number of pages13
JournalComputational Statistics and Data Analysis
Volume54
Issue number1
DOIs
StatePublished - Jan 1 2010

Fingerprint

Trend Test
Genetic Association
Asymptotic Power
Case-control
Matched Case-control Study
Robust Tests
Multi-target Tracking
Chi-squared test
Degree of freedom
Conditional Logistic Regression
Monte Carlo Test
Case-control Data
Matched pairs
Case-control Study
Confounding
p-Value
Stratification
Model
Statistic
Simulation Study

ASJC Scopus subject areas

  • Statistics and Probability
  • Computational Mathematics
  • Computational Theory and Mathematics
  • Applied Mathematics

Cite this

Asymptotic powers for matched trend tests and robust matched trend tests in case-control genetic association studies. / Zang, Yong; Fung, Wing Kam; Zheng, Gang.

In: Computational Statistics and Data Analysis, Vol. 54, No. 1, 01.01.2010, p. 65-77.

Research output: Contribution to journalArticle

@article{06057662cbd046bfbffdd4f01a4fd70e,
title = "Asymptotic powers for matched trend tests and robust matched trend tests in case-control genetic association studies",
abstract = "The matched trend test (MTT), developed using a conditional logistic regression, has been proposed to test for association in matched case-control studies to control the bias of known confounding effects and reduce the potential impact of population stratification. The MTT requires a known genetic model. When the genetic model is unknown, a Monte Carlo robust test, MAX, has been proposed for the analysis of matched case-control studies. The MAX statistic takes the maximum of three MTTs optimal for three common genetic models. We derive the asymptotic power for MTTs and robust tests. In particular, we derive the asymptotic p-value for MAX. Using these analytical results, we conduct simulation studies to compare the performance of MAX and the two-degree-of-freedom Chi-square test for matched case-control studies, where the latter is implemented in most computing software. Our simulation results show that MAX is always asymptotically more powerful than the two-degree-of-freedom Chi-square test under common genetic models. Our results provide guidelines for the analysis of genetic association using matched case-control data. An illustration of our results to a real matched pair case-control etiologic study of sarcoidosis is given.",
author = "Yong Zang and Fung, {Wing Kam} and Gang Zheng",
year = "2010",
month = "1",
day = "1",
doi = "10.1016/j.csda.2009.07.011",
language = "English (US)",
volume = "54",
pages = "65--77",
journal = "Computational Statistics and Data Analysis",
issn = "0167-9473",
publisher = "Elsevier",
number = "1",

}

TY - JOUR

T1 - Asymptotic powers for matched trend tests and robust matched trend tests in case-control genetic association studies

AU - Zang, Yong

AU - Fung, Wing Kam

AU - Zheng, Gang

PY - 2010/1/1

Y1 - 2010/1/1

N2 - The matched trend test (MTT), developed using a conditional logistic regression, has been proposed to test for association in matched case-control studies to control the bias of known confounding effects and reduce the potential impact of population stratification. The MTT requires a known genetic model. When the genetic model is unknown, a Monte Carlo robust test, MAX, has been proposed for the analysis of matched case-control studies. The MAX statistic takes the maximum of three MTTs optimal for three common genetic models. We derive the asymptotic power for MTTs and robust tests. In particular, we derive the asymptotic p-value for MAX. Using these analytical results, we conduct simulation studies to compare the performance of MAX and the two-degree-of-freedom Chi-square test for matched case-control studies, where the latter is implemented in most computing software. Our simulation results show that MAX is always asymptotically more powerful than the two-degree-of-freedom Chi-square test under common genetic models. Our results provide guidelines for the analysis of genetic association using matched case-control data. An illustration of our results to a real matched pair case-control etiologic study of sarcoidosis is given.

AB - The matched trend test (MTT), developed using a conditional logistic regression, has been proposed to test for association in matched case-control studies to control the bias of known confounding effects and reduce the potential impact of population stratification. The MTT requires a known genetic model. When the genetic model is unknown, a Monte Carlo robust test, MAX, has been proposed for the analysis of matched case-control studies. The MAX statistic takes the maximum of three MTTs optimal for three common genetic models. We derive the asymptotic power for MTTs and robust tests. In particular, we derive the asymptotic p-value for MAX. Using these analytical results, we conduct simulation studies to compare the performance of MAX and the two-degree-of-freedom Chi-square test for matched case-control studies, where the latter is implemented in most computing software. Our simulation results show that MAX is always asymptotically more powerful than the two-degree-of-freedom Chi-square test under common genetic models. Our results provide guidelines for the analysis of genetic association using matched case-control data. An illustration of our results to a real matched pair case-control etiologic study of sarcoidosis is given.

UR - http://www.scopus.com/inward/record.url?scp=70349299831&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=70349299831&partnerID=8YFLogxK

U2 - 10.1016/j.csda.2009.07.011

DO - 10.1016/j.csda.2009.07.011

M3 - Article

AN - SCOPUS:70349299831

VL - 54

SP - 65

EP - 77

JO - Computational Statistics and Data Analysis

JF - Computational Statistics and Data Analysis

SN - 0167-9473

IS - 1

ER -