Longitudinal beta-binomial modeling using GEE for overdispersed binomial data

Hongqian Wu, Ying Zhang, Jeffrey D. Long

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Longitudinal binomial data are frequently generated from multiple questionnaires and assessments in various scientific settings for which the binomial data are often overdispersed. The standard generalized linear mixed effects model may result in severe underestimation of standard errors of estimated regression parameters in such cases and hence potentially bias the statistical inference. In this paper, we propose a longitudinal beta-binomial model for overdispersed binomial data and estimate the regression parameters under a probit model using the generalized estimating equation method. A hybrid algorithm of the Fisher scoring and the method of moments is implemented for computing the method. Extensive simulation studies are conducted to justify the validity of the proposed method. Finally, the proposed method is applied to analyze functional impairment in subjects who are at risk of Huntington disease from a multisite observational study of prodromal Huntington disease.

Original languageEnglish (US)
Pages (from-to)1029-1040
Number of pages12
JournalStatistics in Medicine
Volume36
Issue number6
DOIs
StatePublished - Mar 15 2017

Fingerprint

Beta-binomial
Huntington Disease
Modeling
Regression
Fisher Scoring
Beta-binomial Model
Linear Mixed Effects Model
Probit Model
Observational Study
Generalized Estimating Equations
Method of Moments
Statistical Models
Standard error
Hybrid Algorithm
Statistical Inference
Questionnaire
Justify
Observational Studies
Research Design
Simulation Study

Keywords

  • beta-binomial model
  • generalized estimating equation
  • generalized linear mixed-effects model
  • overdispersion
  • probit model

ASJC Scopus subject areas

  • Epidemiology
  • Statistics and Probability

Cite this

Longitudinal beta-binomial modeling using GEE for overdispersed binomial data. / Wu, Hongqian; Zhang, Ying; Long, Jeffrey D.

In: Statistics in Medicine, Vol. 36, No. 6, 15.03.2017, p. 1029-1040.

Research output: Contribution to journalArticle

Wu, Hongqian ; Zhang, Ying ; Long, Jeffrey D. / Longitudinal beta-binomial modeling using GEE for overdispersed binomial data. In: Statistics in Medicine. 2017 ; Vol. 36, No. 6. pp. 1029-1040.
@article{fc551faa8a4a4d158c79ab1eeea42039,
title = "Longitudinal beta-binomial modeling using GEE for overdispersed binomial data",
abstract = "Longitudinal binomial data are frequently generated from multiple questionnaires and assessments in various scientific settings for which the binomial data are often overdispersed. The standard generalized linear mixed effects model may result in severe underestimation of standard errors of estimated regression parameters in such cases and hence potentially bias the statistical inference. In this paper, we propose a longitudinal beta-binomial model for overdispersed binomial data and estimate the regression parameters under a probit model using the generalized estimating equation method. A hybrid algorithm of the Fisher scoring and the method of moments is implemented for computing the method. Extensive simulation studies are conducted to justify the validity of the proposed method. Finally, the proposed method is applied to analyze functional impairment in subjects who are at risk of Huntington disease from a multisite observational study of prodromal Huntington disease.",
keywords = "beta-binomial model, generalized estimating equation, generalized linear mixed-effects model, overdispersion, probit model",
author = "Hongqian Wu and Ying Zhang and Long, {Jeffrey D.}",
year = "2017",
month = "3",
day = "15",
doi = "10.1002/sim.7191",
language = "English (US)",
volume = "36",
pages = "1029--1040",
journal = "Statistics in Medicine",
issn = "0277-6715",
publisher = "John Wiley and Sons Ltd",
number = "6",

}

TY - JOUR

T1 - Longitudinal beta-binomial modeling using GEE for overdispersed binomial data

AU - Wu, Hongqian

AU - Zhang, Ying

AU - Long, Jeffrey D.

PY - 2017/3/15

Y1 - 2017/3/15

N2 - Longitudinal binomial data are frequently generated from multiple questionnaires and assessments in various scientific settings for which the binomial data are often overdispersed. The standard generalized linear mixed effects model may result in severe underestimation of standard errors of estimated regression parameters in such cases and hence potentially bias the statistical inference. In this paper, we propose a longitudinal beta-binomial model for overdispersed binomial data and estimate the regression parameters under a probit model using the generalized estimating equation method. A hybrid algorithm of the Fisher scoring and the method of moments is implemented for computing the method. Extensive simulation studies are conducted to justify the validity of the proposed method. Finally, the proposed method is applied to analyze functional impairment in subjects who are at risk of Huntington disease from a multisite observational study of prodromal Huntington disease.

AB - Longitudinal binomial data are frequently generated from multiple questionnaires and assessments in various scientific settings for which the binomial data are often overdispersed. The standard generalized linear mixed effects model may result in severe underestimation of standard errors of estimated regression parameters in such cases and hence potentially bias the statistical inference. In this paper, we propose a longitudinal beta-binomial model for overdispersed binomial data and estimate the regression parameters under a probit model using the generalized estimating equation method. A hybrid algorithm of the Fisher scoring and the method of moments is implemented for computing the method. Extensive simulation studies are conducted to justify the validity of the proposed method. Finally, the proposed method is applied to analyze functional impairment in subjects who are at risk of Huntington disease from a multisite observational study of prodromal Huntington disease.

KW - beta-binomial model

KW - generalized estimating equation

KW - generalized linear mixed-effects model

KW - overdispersion

KW - probit model

UR - http://www.scopus.com/inward/record.url?scp=85006351488&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85006351488&partnerID=8YFLogxK

U2 - 10.1002/sim.7191

DO - 10.1002/sim.7191

M3 - Article

VL - 36

SP - 1029

EP - 1040

JO - Statistics in Medicine

JF - Statistics in Medicine

SN - 0277-6715

IS - 6

ER -