Strategy to Control Type I Error Increases Power to Identify Genetic Variation Using the Full Biological Trajectory

Research output: Contribution to journalArticle

Abstract

Genome-wide association studies have been successful in identifying loci that underlie continuous traits measured at a single time point. To additionally consider continuous traits longitudinally, it is desirable to look at SNP effects at baseline and over time using linear-mixed effects models. Estimation and interpretation of two coefficients in the same model raises concern regarding the optimal control of type I error. To investigate this issue, we calculate type I error and power under an alternative for joint tests, including the two degree of freedom likelihood ratio test, and compare this to single degree of freedom tests for each effect separately at varying alpha levels. We show which joint tests are the optimal way to control the type I error and also illustrate that information can be gained by joint testing in situations where either or both SNP effects are underpowered. We also show that closed form power calculations can approximate simulated power for the case of balanced data, provide reasonable approximations for imbalanced data, but overestimate power for complicated residual error structures. We conclude that a two degree of freedom test is an attractive strategy in a hypothesis-free genome-wide setting and recommend its use for genome-wide studies employing linear-mixed effects models.

Original languageEnglish (US)
Pages (from-to)419-430
Number of pages12
JournalGenetic Epidemiology
Volume37
Issue number5
DOIs
StatePublished - Jul 2013

Fingerprint

Joints
Single Nucleotide Polymorphism
Genome
Genome-Wide Association Study

Keywords

  • Genome-wide association study
  • Linear-mixed effects model
  • Longitudinal data
  • Power and type I error calculations

ASJC Scopus subject areas

  • Genetics(clinical)
  • Epidemiology

Cite this

@article{d578c088399942e18c198148c1401a16,
title = "Strategy to Control Type I Error Increases Power to Identify Genetic Variation Using the Full Biological Trajectory",
abstract = "Genome-wide association studies have been successful in identifying loci that underlie continuous traits measured at a single time point. To additionally consider continuous traits longitudinally, it is desirable to look at SNP effects at baseline and over time using linear-mixed effects models. Estimation and interpretation of two coefficients in the same model raises concern regarding the optimal control of type I error. To investigate this issue, we calculate type I error and power under an alternative for joint tests, including the two degree of freedom likelihood ratio test, and compare this to single degree of freedom tests for each effect separately at varying alpha levels. We show which joint tests are the optimal way to control the type I error and also illustrate that information can be gained by joint testing in situations where either or both SNP effects are underpowered. We also show that closed form power calculations can approximate simulated power for the case of balanced data, provide reasonable approximations for imbalanced data, but overestimate power for complicated residual error structures. We conclude that a two degree of freedom test is an attractive strategy in a hypothesis-free genome-wide setting and recommend its use for genome-wide studies employing linear-mixed effects models.",
keywords = "Genome-wide association study, Linear-mixed effects model, Longitudinal data, Power and type I error calculations",
author = "Kelly Benke and Y. Wu and Fallin, {Daniele Daniele} and Brion Maher and Palmer, {L. J.}",
year = "2013",
month = "7",
doi = "10.1002/gepi.21733",
language = "English (US)",
volume = "37",
pages = "419--430",
journal = "Genetic Epidemiology",
issn = "0741-0395",
publisher = "Wiley-Liss Inc.",
number = "5",

}

TY - JOUR

T1 - Strategy to Control Type I Error Increases Power to Identify Genetic Variation Using the Full Biological Trajectory

AU - Benke, Kelly

AU - Wu, Y.

AU - Fallin, Daniele Daniele

AU - Maher, Brion

AU - Palmer, L. J.

PY - 2013/7

Y1 - 2013/7

N2 - Genome-wide association studies have been successful in identifying loci that underlie continuous traits measured at a single time point. To additionally consider continuous traits longitudinally, it is desirable to look at SNP effects at baseline and over time using linear-mixed effects models. Estimation and interpretation of two coefficients in the same model raises concern regarding the optimal control of type I error. To investigate this issue, we calculate type I error and power under an alternative for joint tests, including the two degree of freedom likelihood ratio test, and compare this to single degree of freedom tests for each effect separately at varying alpha levels. We show which joint tests are the optimal way to control the type I error and also illustrate that information can be gained by joint testing in situations where either or both SNP effects are underpowered. We also show that closed form power calculations can approximate simulated power for the case of balanced data, provide reasonable approximations for imbalanced data, but overestimate power for complicated residual error structures. We conclude that a two degree of freedom test is an attractive strategy in a hypothesis-free genome-wide setting and recommend its use for genome-wide studies employing linear-mixed effects models.

AB - Genome-wide association studies have been successful in identifying loci that underlie continuous traits measured at a single time point. To additionally consider continuous traits longitudinally, it is desirable to look at SNP effects at baseline and over time using linear-mixed effects models. Estimation and interpretation of two coefficients in the same model raises concern regarding the optimal control of type I error. To investigate this issue, we calculate type I error and power under an alternative for joint tests, including the two degree of freedom likelihood ratio test, and compare this to single degree of freedom tests for each effect separately at varying alpha levels. We show which joint tests are the optimal way to control the type I error and also illustrate that information can be gained by joint testing in situations where either or both SNP effects are underpowered. We also show that closed form power calculations can approximate simulated power for the case of balanced data, provide reasonable approximations for imbalanced data, but overestimate power for complicated residual error structures. We conclude that a two degree of freedom test is an attractive strategy in a hypothesis-free genome-wide setting and recommend its use for genome-wide studies employing linear-mixed effects models.

KW - Genome-wide association study

KW - Linear-mixed effects model

KW - Longitudinal data

KW - Power and type I error calculations

UR - http://www.scopus.com/inward/record.url?scp=84879155219&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84879155219&partnerID=8YFLogxK

U2 - 10.1002/gepi.21733

DO - 10.1002/gepi.21733

M3 - Article

C2 - 23633177

AN - SCOPUS:84879155219

VL - 37

SP - 419

EP - 430

JO - Genetic Epidemiology

JF - Genetic Epidemiology

SN - 0741-0395

IS - 5

ER -