Poor performance of bootstrap confidence intervals for the location of a quantitative trait locus

Ani Manichaikul, Josée Dupuis, Saunak Sen, Karl W. Broman

Research output: Contribution to journalArticle

107 Citations (Scopus)

Abstract

The aim of many genetic studies is to locate the genomic regions (called quantitative trait loci, QTL) that contribute to variation in a quantitative trait (such as body weight). Confidence intervals for the locations of QTL are particularly important for the design of further experiments to identify the gene or genes responsible for the effect. Likelihood support intervals are the most widely used method to obtain confidence intervals for QTL location, but the nonparametric bootstrap has also been recommended. Through extensive computer simulation, we show that bootstrap confidence intervals behave poorly and so should not be used in this context. The profile likelihood (or LOD curve) for QTL location has a tendency to peak at genetic markers, and so the distribution of the maximum-likelihood estimate (MLE) of QTL location has the unusual feature of point masses at genetic markers; this contributes to the poor behavior of the bootstrap. Likelihood support intervals and approximate Bayes credible intervals, on the other hand, are shown to behave appropriately.

Original languageEnglish (US)
Pages (from-to)481-489
Number of pages9
JournalGenetics
Volume174
Issue number1
DOIs
StatePublished - Sep 27 2006

Fingerprint

Quantitative Trait Loci
Confidence Intervals
Genetic Markers
Likelihood Functions
Computer Simulation
Genes
Body Weight

All Science Journal Classification (ASJC) codes

  • Genetics

Cite this

Poor performance of bootstrap confidence intervals for the location of a quantitative trait locus. / Manichaikul, Ani; Dupuis, Josée; Sen, Saunak; Broman, Karl W.

In: Genetics, Vol. 174, No. 1, 27.09.2006, p. 481-489.

Research output: Contribution to journalArticle

Manichaikul, Ani ; Dupuis, Josée ; Sen, Saunak ; Broman, Karl W. / Poor performance of bootstrap confidence intervals for the location of a quantitative trait locus. In: Genetics. 2006 ; Vol. 174, No. 1. pp. 481-489.
@article{b6dea4da849448fcbc81d310190a7dbb,
title = "Poor performance of bootstrap confidence intervals for the location of a quantitative trait locus",
abstract = "The aim of many genetic studies is to locate the genomic regions (called quantitative trait loci, QTL) that contribute to variation in a quantitative trait (such as body weight). Confidence intervals for the locations of QTL are particularly important for the design of further experiments to identify the gene or genes responsible for the effect. Likelihood support intervals are the most widely used method to obtain confidence intervals for QTL location, but the nonparametric bootstrap has also been recommended. Through extensive computer simulation, we show that bootstrap confidence intervals behave poorly and so should not be used in this context. The profile likelihood (or LOD curve) for QTL location has a tendency to peak at genetic markers, and so the distribution of the maximum-likelihood estimate (MLE) of QTL location has the unusual feature of point masses at genetic markers; this contributes to the poor behavior of the bootstrap. Likelihood support intervals and approximate Bayes credible intervals, on the other hand, are shown to behave appropriately.",
author = "Ani Manichaikul and Jos{\'e}e Dupuis and Saunak Sen and Broman, {Karl W.}",
year = "2006",
month = "9",
day = "27",
doi = "10.1534/genetics.106.061549",
language = "English (US)",
volume = "174",
pages = "481--489",
journal = "Genetics",
issn = "0016-6731",
publisher = "Genetics Society of America",
number = "1",

}

TY - JOUR

T1 - Poor performance of bootstrap confidence intervals for the location of a quantitative trait locus

AU - Manichaikul, Ani

AU - Dupuis, Josée

AU - Sen, Saunak

AU - Broman, Karl W.

PY - 2006/9/27

Y1 - 2006/9/27

N2 - The aim of many genetic studies is to locate the genomic regions (called quantitative trait loci, QTL) that contribute to variation in a quantitative trait (such as body weight). Confidence intervals for the locations of QTL are particularly important for the design of further experiments to identify the gene or genes responsible for the effect. Likelihood support intervals are the most widely used method to obtain confidence intervals for QTL location, but the nonparametric bootstrap has also been recommended. Through extensive computer simulation, we show that bootstrap confidence intervals behave poorly and so should not be used in this context. The profile likelihood (or LOD curve) for QTL location has a tendency to peak at genetic markers, and so the distribution of the maximum-likelihood estimate (MLE) of QTL location has the unusual feature of point masses at genetic markers; this contributes to the poor behavior of the bootstrap. Likelihood support intervals and approximate Bayes credible intervals, on the other hand, are shown to behave appropriately.

AB - The aim of many genetic studies is to locate the genomic regions (called quantitative trait loci, QTL) that contribute to variation in a quantitative trait (such as body weight). Confidence intervals for the locations of QTL are particularly important for the design of further experiments to identify the gene or genes responsible for the effect. Likelihood support intervals are the most widely used method to obtain confidence intervals for QTL location, but the nonparametric bootstrap has also been recommended. Through extensive computer simulation, we show that bootstrap confidence intervals behave poorly and so should not be used in this context. The profile likelihood (or LOD curve) for QTL location has a tendency to peak at genetic markers, and so the distribution of the maximum-likelihood estimate (MLE) of QTL location has the unusual feature of point masses at genetic markers; this contributes to the poor behavior of the bootstrap. Likelihood support intervals and approximate Bayes credible intervals, on the other hand, are shown to behave appropriately.

UR - http://www.scopus.com/inward/record.url?scp=33748900748&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33748900748&partnerID=8YFLogxK

U2 - 10.1534/genetics.106.061549

DO - 10.1534/genetics.106.061549

M3 - Article

C2 - 16783000

AN - SCOPUS:33748900748

VL - 174

SP - 481

EP - 489

JO - Genetics

JF - Genetics

SN - 0016-6731

IS - 1

ER -