A method for evaluating the results of Bayesian model selection: Application to linkage analyses of attributes determined by two or more genes

Young Ju Suh, Qian K. Ye, Nancy R. Mendell

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

Objectives: We apply and evaluate the intrinsic Bayes factor (IBF) of Berger and Pericchi [J Am Stat Assoc 1996;91:109-122; Bayesian Statistics, Oxford University Press, vol 5, 1996] to linkage analyses done using the stochastic search variable selection (SSVS) method of George and McCulloch [J Am Stat Assoc 1993;88:881-889] as proposed by Suh et al. [Genet Epidemiol 2001;21(suppl 1):S706-S711]. Methods: We consider 20 simulations of linkage data obtained under two different generating models. The SSVS is applied to a multiple regression extension [Genet Epidemiol 2001;21(suppl 1): S706-S711] of the Haseman-Elston [Behav Genet 1972;2:3-19; Genet Epidemiol 2000;19:1-17] methods. Four prior distributions are considered. We apply the IBF criterion to those samples where different prior distributions result in different top models. Results: In those samples where three different models were obtained using the four priors, application of the IBFs eliminated one of the two wrong models in 4 out of 5 situations. Further elimination using the IBF criterion for situations with two different subsets did not serve as well. Conclusions: When different priors result in three or more different subsets of markers, one can use the IBF to get this number down to two for consideration. When two subsets result we recommend that both be considered.

Original languageEnglish (US)
Pages (from-to)147-152
Number of pages6
JournalHuman Heredity
Volume55
Issue number2-3
DOIs
StatePublished - 2003
Externally publishedYes

Fingerprint

Viverridae
Intrinsic Factor
Genes
Information Storage and Retrieval

Keywords

  • Intrinsic Bayes factor
  • Linkage
  • Quantitative trait
  • Stochastic search variable selection

ASJC Scopus subject areas

  • Genetics(clinical)

Cite this

A method for evaluating the results of Bayesian model selection : Application to linkage analyses of attributes determined by two or more genes. / Suh, Young Ju; Ye, Qian K.; Mendell, Nancy R.

In: Human Heredity, Vol. 55, No. 2-3, 2003, p. 147-152.

Research output: Contribution to journalArticle

@article{54d20b3a35d04a73803556964a974be4,
title = "A method for evaluating the results of Bayesian model selection: Application to linkage analyses of attributes determined by two or more genes",
abstract = "Objectives: We apply and evaluate the intrinsic Bayes factor (IBF) of Berger and Pericchi [J Am Stat Assoc 1996;91:109-122; Bayesian Statistics, Oxford University Press, vol 5, 1996] to linkage analyses done using the stochastic search variable selection (SSVS) method of George and McCulloch [J Am Stat Assoc 1993;88:881-889] as proposed by Suh et al. [Genet Epidemiol 2001;21(suppl 1):S706-S711]. Methods: We consider 20 simulations of linkage data obtained under two different generating models. The SSVS is applied to a multiple regression extension [Genet Epidemiol 2001;21(suppl 1): S706-S711] of the Haseman-Elston [Behav Genet 1972;2:3-19; Genet Epidemiol 2000;19:1-17] methods. Four prior distributions are considered. We apply the IBF criterion to those samples where different prior distributions result in different top models. Results: In those samples where three different models were obtained using the four priors, application of the IBFs eliminated one of the two wrong models in 4 out of 5 situations. Further elimination using the IBF criterion for situations with two different subsets did not serve as well. Conclusions: When different priors result in three or more different subsets of markers, one can use the IBF to get this number down to two for consideration. When two subsets result we recommend that both be considered.",
keywords = "Intrinsic Bayes factor, Linkage, Quantitative trait, Stochastic search variable selection",
author = "Suh, {Young Ju} and Ye, {Qian K.} and Mendell, {Nancy R.}",
year = "2003",
doi = "10.1159/000072320",
language = "English (US)",
volume = "55",
pages = "147--152",
journal = "Human Heredity",
issn = "0001-5652",
publisher = "S. Karger AG",
number = "2-3",

}

TY - JOUR

T1 - A method for evaluating the results of Bayesian model selection

T2 - Application to linkage analyses of attributes determined by two or more genes

AU - Suh, Young Ju

AU - Ye, Qian K.

AU - Mendell, Nancy R.

PY - 2003

Y1 - 2003

N2 - Objectives: We apply and evaluate the intrinsic Bayes factor (IBF) of Berger and Pericchi [J Am Stat Assoc 1996;91:109-122; Bayesian Statistics, Oxford University Press, vol 5, 1996] to linkage analyses done using the stochastic search variable selection (SSVS) method of George and McCulloch [J Am Stat Assoc 1993;88:881-889] as proposed by Suh et al. [Genet Epidemiol 2001;21(suppl 1):S706-S711]. Methods: We consider 20 simulations of linkage data obtained under two different generating models. The SSVS is applied to a multiple regression extension [Genet Epidemiol 2001;21(suppl 1): S706-S711] of the Haseman-Elston [Behav Genet 1972;2:3-19; Genet Epidemiol 2000;19:1-17] methods. Four prior distributions are considered. We apply the IBF criterion to those samples where different prior distributions result in different top models. Results: In those samples where three different models were obtained using the four priors, application of the IBFs eliminated one of the two wrong models in 4 out of 5 situations. Further elimination using the IBF criterion for situations with two different subsets did not serve as well. Conclusions: When different priors result in three or more different subsets of markers, one can use the IBF to get this number down to two for consideration. When two subsets result we recommend that both be considered.

AB - Objectives: We apply and evaluate the intrinsic Bayes factor (IBF) of Berger and Pericchi [J Am Stat Assoc 1996;91:109-122; Bayesian Statistics, Oxford University Press, vol 5, 1996] to linkage analyses done using the stochastic search variable selection (SSVS) method of George and McCulloch [J Am Stat Assoc 1993;88:881-889] as proposed by Suh et al. [Genet Epidemiol 2001;21(suppl 1):S706-S711]. Methods: We consider 20 simulations of linkage data obtained under two different generating models. The SSVS is applied to a multiple regression extension [Genet Epidemiol 2001;21(suppl 1): S706-S711] of the Haseman-Elston [Behav Genet 1972;2:3-19; Genet Epidemiol 2000;19:1-17] methods. Four prior distributions are considered. We apply the IBF criterion to those samples where different prior distributions result in different top models. Results: In those samples where three different models were obtained using the four priors, application of the IBFs eliminated one of the two wrong models in 4 out of 5 situations. Further elimination using the IBF criterion for situations with two different subsets did not serve as well. Conclusions: When different priors result in three or more different subsets of markers, one can use the IBF to get this number down to two for consideration. When two subsets result we recommend that both be considered.

KW - Intrinsic Bayes factor

KW - Linkage

KW - Quantitative trait

KW - Stochastic search variable selection

UR - http://www.scopus.com/inward/record.url?scp=0042385042&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0042385042&partnerID=8YFLogxK

U2 - 10.1159/000072320

DO - 10.1159/000072320

M3 - Article

C2 - 12931054

AN - SCOPUS:0042385042

VL - 55

SP - 147

EP - 152

JO - Human Heredity

JF - Human Heredity

SN - 0001-5652

IS - 2-3

ER -