The robustness of generalized estimating equations for association tests in extended family data

Research output: Contribution to journalArticle

Abstract

Variance components analysis (VCA), the traditional method for handling correlations within families in genetic association studies, is computationally intensive for genome-wide analyses, and the computational burden of VCA increases with family size and the number of genetic markers. Alternative approaches that do not require the computation of familial correlations are preferable, provided that they do not inflate type I error or decrease power. We performed a simulation study to evaluate practical alternatives to VCA that use regression with generalized estimating equations (GEE) in extended family data. We compared the properties of linear regression with GEE applied to an entire extended family structure (GEE-EXT) and GEE applied to nuclear family structures split from these extended families (GEE-SPL) to variance components likelihood-based methods (FastAssoc). GEE-EXT was evaluated with and without robust variance estimators to estimate the standard errors. We observed similar average type I error rates from GEE-EXT and FastAssoc compared to GEE-SPL. Type I error rates for the GEE-EXT method with a robust variance estimator were marginally higher than the nominal rate when the minor allele frequency (MAF) was

Original languageEnglish (US)
Pages (from-to)17-26
Number of pages10
JournalHuman Heredity
Volume74
Issue number1
DOIs
StatePublished - Nov 2012

Fingerprint

Analysis of Variance
Genetic Association Studies
Nuclear Family
Genetic Markers
Gene Frequency
Linear Models
Genome
Power (Psychology)

Keywords

  • Family-based association study
  • Generalized estimating equation
  • Genome-wide scan
  • Variance components analysis

ASJC Scopus subject areas

  • Genetics(clinical)
  • Genetics

Cite this

@article{54540d46b2c247e0ade95fceb9a392ce,
title = "The robustness of generalized estimating equations for association tests in extended family data",
abstract = "Variance components analysis (VCA), the traditional method for handling correlations within families in genetic association studies, is computationally intensive for genome-wide analyses, and the computational burden of VCA increases with family size and the number of genetic markers. Alternative approaches that do not require the computation of familial correlations are preferable, provided that they do not inflate type I error or decrease power. We performed a simulation study to evaluate practical alternatives to VCA that use regression with generalized estimating equations (GEE) in extended family data. We compared the properties of linear regression with GEE applied to an entire extended family structure (GEE-EXT) and GEE applied to nuclear family structures split from these extended families (GEE-SPL) to variance components likelihood-based methods (FastAssoc). GEE-EXT was evaluated with and without robust variance estimators to estimate the standard errors. We observed similar average type I error rates from GEE-EXT and FastAssoc compared to GEE-SPL. Type I error rates for the GEE-EXT method with a robust variance estimator were marginally higher than the nominal rate when the minor allele frequency (MAF) was",
keywords = "Family-based association study, Generalized estimating equation, Genome-wide scan, Variance components analysis",
author = "Bhoom Suktitipat and Rasika Mathias and Dhananjay Vaidya and Lisa Yanek and Young, {J Hunter} and Lewis Becker and Becker, {Diane M} and Wilson, {Alexander F.} and Fallin, {Daniele Daniele}",
year = "2012",
month = "11",
doi = "10.1159/000341636",
language = "English (US)",
volume = "74",
pages = "17--26",
journal = "Human Heredity",
issn = "0001-5652",
publisher = "S. Karger AG",
number = "1",

}

TY - JOUR

T1 - The robustness of generalized estimating equations for association tests in extended family data

AU - Suktitipat, Bhoom

AU - Mathias, Rasika

AU - Vaidya, Dhananjay

AU - Yanek, Lisa

AU - Young, J Hunter

AU - Becker, Lewis

AU - Becker, Diane M

AU - Wilson, Alexander F.

AU - Fallin, Daniele Daniele

PY - 2012/11

Y1 - 2012/11

N2 - Variance components analysis (VCA), the traditional method for handling correlations within families in genetic association studies, is computationally intensive for genome-wide analyses, and the computational burden of VCA increases with family size and the number of genetic markers. Alternative approaches that do not require the computation of familial correlations are preferable, provided that they do not inflate type I error or decrease power. We performed a simulation study to evaluate practical alternatives to VCA that use regression with generalized estimating equations (GEE) in extended family data. We compared the properties of linear regression with GEE applied to an entire extended family structure (GEE-EXT) and GEE applied to nuclear family structures split from these extended families (GEE-SPL) to variance components likelihood-based methods (FastAssoc). GEE-EXT was evaluated with and without robust variance estimators to estimate the standard errors. We observed similar average type I error rates from GEE-EXT and FastAssoc compared to GEE-SPL. Type I error rates for the GEE-EXT method with a robust variance estimator were marginally higher than the nominal rate when the minor allele frequency (MAF) was

AB - Variance components analysis (VCA), the traditional method for handling correlations within families in genetic association studies, is computationally intensive for genome-wide analyses, and the computational burden of VCA increases with family size and the number of genetic markers. Alternative approaches that do not require the computation of familial correlations are preferable, provided that they do not inflate type I error or decrease power. We performed a simulation study to evaluate practical alternatives to VCA that use regression with generalized estimating equations (GEE) in extended family data. We compared the properties of linear regression with GEE applied to an entire extended family structure (GEE-EXT) and GEE applied to nuclear family structures split from these extended families (GEE-SPL) to variance components likelihood-based methods (FastAssoc). GEE-EXT was evaluated with and without robust variance estimators to estimate the standard errors. We observed similar average type I error rates from GEE-EXT and FastAssoc compared to GEE-SPL. Type I error rates for the GEE-EXT method with a robust variance estimator were marginally higher than the nominal rate when the minor allele frequency (MAF) was

KW - Family-based association study

KW - Generalized estimating equation

KW - Genome-wide scan

KW - Variance components analysis

UR - http://www.scopus.com/inward/record.url?scp=84866930515&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84866930515&partnerID=8YFLogxK

U2 - 10.1159/000341636

DO - 10.1159/000341636

M3 - Article

C2 - 23038411

AN - SCOPUS:84866930515

VL - 74

SP - 17

EP - 26

JO - Human Heredity

JF - Human Heredity

SN - 0001-5652

IS - 1

ER -