A general class of pattern mixture models for nonignorable dropout with many possible dropout times

Jason Roy, Michael J. Daniels

Research output: Contribution to journalArticle

28 Citations (Scopus)

Abstract

In this article we consider the problem of fitting pattern mixture models to longitudinal data when there are many unique dropout times. We propose a marginally specified latent class pattern mixture model. The marginal mean is assumed to follow a generalized linear model, whereas the mean conditional on the latent class and random effects is specified separately. Because the dimension of the parameter vector of interest (the marginal regression coefficients) does not depend on the assumed number of latent classes, we propose to treat the number of latent classes as a random variable. We specify a prior distribution for the number of classes, and calculate (approximate) posterior model probabilities. In order to avoid the complications with implementing a fully Bayesian model, we propose a simple approximation to these posterior probabilities. The ideas are illustrated using data from a longitudinal study of depression in HIV-infected women.

Original languageEnglish (US)
Pages (from-to)538-545
Number of pages8
JournalBiometrics
Volume64
Issue number2
DOIs
StatePublished - Jun 1 2008
Externally publishedYes

Fingerprint

Pattern-mixture Model
dropouts
Latent Class
Drop out
Longitudinal Studies
Latent Class Model
Linear Models
Longitudinal Study
Probability Model
Posterior Probability
HIV
Generalized Linear Model
Bayesian Model
Longitudinal Data
Regression Coefficient
Prior distribution
Complications
Random Effects
longitudinal studies
Random variable

All Science Journal Classification (ASJC) codes

  • Agricultural and Biological Sciences(all)
  • Public Health, Environmental and Occupational Health
  • Applied Mathematics
  • Agricultural and Biological Sciences (miscellaneous)
  • Statistics and Probability

Cite this

@article{2b83e32ebd4641cb9a4981bdf18716b8,
title = "A general class of pattern mixture models for nonignorable dropout with many possible dropout times",
abstract = "In this article we consider the problem of fitting pattern mixture models to longitudinal data when there are many unique dropout times. We propose a marginally specified latent class pattern mixture model. The marginal mean is assumed to follow a generalized linear model, whereas the mean conditional on the latent class and random effects is specified separately. Because the dimension of the parameter vector of interest (the marginal regression coefficients) does not depend on the assumed number of latent classes, we propose to treat the number of latent classes as a random variable. We specify a prior distribution for the number of classes, and calculate (approximate) posterior model probabilities. In order to avoid the complications with implementing a fully Bayesian model, we propose a simple approximation to these posterior probabilities. The ideas are illustrated using data from a longitudinal study of depression in HIV-infected women.",
author = "Jason Roy and Daniels, {Michael J.}",
year = "2008",
month = "6",
day = "1",
doi = "https://doi.org/10.1111/j.1541-0420.2007.00884.x",
language = "English (US)",
volume = "64",
pages = "538--545",
journal = "Biometrics",
issn = "0006-341X",
publisher = "Wiley-Blackwell",
number = "2",

}

A general class of pattern mixture models for nonignorable dropout with many possible dropout times. / Roy, Jason; Daniels, Michael J.

In: Biometrics, Vol. 64, No. 2, 01.06.2008, p. 538-545.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A general class of pattern mixture models for nonignorable dropout with many possible dropout times

AU - Roy, Jason

AU - Daniels, Michael J.

PY - 2008/6/1

Y1 - 2008/6/1

N2 - In this article we consider the problem of fitting pattern mixture models to longitudinal data when there are many unique dropout times. We propose a marginally specified latent class pattern mixture model. The marginal mean is assumed to follow a generalized linear model, whereas the mean conditional on the latent class and random effects is specified separately. Because the dimension of the parameter vector of interest (the marginal regression coefficients) does not depend on the assumed number of latent classes, we propose to treat the number of latent classes as a random variable. We specify a prior distribution for the number of classes, and calculate (approximate) posterior model probabilities. In order to avoid the complications with implementing a fully Bayesian model, we propose a simple approximation to these posterior probabilities. The ideas are illustrated using data from a longitudinal study of depression in HIV-infected women.

AB - In this article we consider the problem of fitting pattern mixture models to longitudinal data when there are many unique dropout times. We propose a marginally specified latent class pattern mixture model. The marginal mean is assumed to follow a generalized linear model, whereas the mean conditional on the latent class and random effects is specified separately. Because the dimension of the parameter vector of interest (the marginal regression coefficients) does not depend on the assumed number of latent classes, we propose to treat the number of latent classes as a random variable. We specify a prior distribution for the number of classes, and calculate (approximate) posterior model probabilities. In order to avoid the complications with implementing a fully Bayesian model, we propose a simple approximation to these posterior probabilities. The ideas are illustrated using data from a longitudinal study of depression in HIV-infected women.

UR - http://www.scopus.com/inward/record.url?scp=43749111782&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=43749111782&partnerID=8YFLogxK

U2 - https://doi.org/10.1111/j.1541-0420.2007.00884.x

DO - https://doi.org/10.1111/j.1541-0420.2007.00884.x

M3 - Article

VL - 64

SP - 538

EP - 545

JO - Biometrics

JF - Biometrics

SN - 0006-341X

IS - 2

ER -