Bayesian Variable Selection in Multilevel Item Response Theory Models with Application in Genomics

Tiago M. Fragoso, Mariza De Andrade, Alexandre C. Pereira, Guilherme J M Rosa, Júlia M P Soler

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

The goal of this paper is to present an implementation of stochastic search variable selection (SSVS) to multilevel model from item response theory (IRT). As experimental settings get more complex and models are required to integrate multiple (and sometimes massive) sources of information, a model that can jointly summarize and select the most relevant characteristics can provide better interpretation and a deeper insight into the problem. A multilevel IRT model recently proposed in the literature for modeling multifactorial diseases is extended to perform variable selection in the presence of thousands of covariates using SSVS. We derive conditional distributions required for such a task as well as an acceptance-rejection step that allows for the SSVS in high dimensional settings using a Markov Chain Monte Carlo algorithm. We validate the variable selection procedure through simulation studies, and illustrate its application on a study with genetic markers associated with the metabolic syndrome.

Original languageEnglish (US)
Pages (from-to)253-263
Number of pages11
JournalGenetic Epidemiology
Volume40
Issue number3
DOIs
StatePublished - Apr 1 2016

Fingerprint

Markov Chains
Genomics
Genetic Markers

Keywords

  • Data augmentation
  • MCMC
  • Metabolic syndrome
  • Stochastic search variable selection

ASJC Scopus subject areas

  • Genetics(clinical)
  • Epidemiology

Cite this

Bayesian Variable Selection in Multilevel Item Response Theory Models with Application in Genomics. / Fragoso, Tiago M.; De Andrade, Mariza; Pereira, Alexandre C.; Rosa, Guilherme J M; Soler, Júlia M P.

In: Genetic Epidemiology, Vol. 40, No. 3, 01.04.2016, p. 253-263.

Research output: Contribution to journalArticle

Fragoso, Tiago M. ; De Andrade, Mariza ; Pereira, Alexandre C. ; Rosa, Guilherme J M ; Soler, Júlia M P. / Bayesian Variable Selection in Multilevel Item Response Theory Models with Application in Genomics. In: Genetic Epidemiology. 2016 ; Vol. 40, No. 3. pp. 253-263.
@article{e5e259c8e97b42e984f1dc36f8ddbebd,
title = "Bayesian Variable Selection in Multilevel Item Response Theory Models with Application in Genomics",
abstract = "The goal of this paper is to present an implementation of stochastic search variable selection (SSVS) to multilevel model from item response theory (IRT). As experimental settings get more complex and models are required to integrate multiple (and sometimes massive) sources of information, a model that can jointly summarize and select the most relevant characteristics can provide better interpretation and a deeper insight into the problem. A multilevel IRT model recently proposed in the literature for modeling multifactorial diseases is extended to perform variable selection in the presence of thousands of covariates using SSVS. We derive conditional distributions required for such a task as well as an acceptance-rejection step that allows for the SSVS in high dimensional settings using a Markov Chain Monte Carlo algorithm. We validate the variable selection procedure through simulation studies, and illustrate its application on a study with genetic markers associated with the metabolic syndrome.",
keywords = "Data augmentation, MCMC, Metabolic syndrome, Stochastic search variable selection",
author = "Fragoso, {Tiago M.} and {De Andrade}, Mariza and Pereira, {Alexandre C.} and Rosa, {Guilherme J M} and Soler, {J{\'u}lia M P}",
year = "2016",
month = "4",
day = "1",
doi = "10.1002/gepi.21960",
language = "English (US)",
volume = "40",
pages = "253--263",
journal = "Genetic Epidemiology",
issn = "0741-0395",
publisher = "Wiley-Liss Inc.",
number = "3",

}

TY - JOUR

T1 - Bayesian Variable Selection in Multilevel Item Response Theory Models with Application in Genomics

AU - Fragoso, Tiago M.

AU - De Andrade, Mariza

AU - Pereira, Alexandre C.

AU - Rosa, Guilherme J M

AU - Soler, Júlia M P

PY - 2016/4/1

Y1 - 2016/4/1

N2 - The goal of this paper is to present an implementation of stochastic search variable selection (SSVS) to multilevel model from item response theory (IRT). As experimental settings get more complex and models are required to integrate multiple (and sometimes massive) sources of information, a model that can jointly summarize and select the most relevant characteristics can provide better interpretation and a deeper insight into the problem. A multilevel IRT model recently proposed in the literature for modeling multifactorial diseases is extended to perform variable selection in the presence of thousands of covariates using SSVS. We derive conditional distributions required for such a task as well as an acceptance-rejection step that allows for the SSVS in high dimensional settings using a Markov Chain Monte Carlo algorithm. We validate the variable selection procedure through simulation studies, and illustrate its application on a study with genetic markers associated with the metabolic syndrome.

AB - The goal of this paper is to present an implementation of stochastic search variable selection (SSVS) to multilevel model from item response theory (IRT). As experimental settings get more complex and models are required to integrate multiple (and sometimes massive) sources of information, a model that can jointly summarize and select the most relevant characteristics can provide better interpretation and a deeper insight into the problem. A multilevel IRT model recently proposed in the literature for modeling multifactorial diseases is extended to perform variable selection in the presence of thousands of covariates using SSVS. We derive conditional distributions required for such a task as well as an acceptance-rejection step that allows for the SSVS in high dimensional settings using a Markov Chain Monte Carlo algorithm. We validate the variable selection procedure through simulation studies, and illustrate its application on a study with genetic markers associated with the metabolic syndrome.

KW - Data augmentation

KW - MCMC

KW - Metabolic syndrome

KW - Stochastic search variable selection

UR - http://www.scopus.com/inward/record.url?scp=84961955662&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84961955662&partnerID=8YFLogxK

U2 - 10.1002/gepi.21960

DO - 10.1002/gepi.21960

M3 - Article

VL - 40

SP - 253

EP - 263

JO - Genetic Epidemiology

JF - Genetic Epidemiology

SN - 0741-0395

IS - 3

ER -