A correlated random effects model for non-homogeneous Markov processes with nonignorable missingness

Baojiang Chen, Xiao Hua Zhou

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

Life history data arising in clusters with pre-specified assessment time points for patients often feature incomplete data since patients may choose to visit the clinic based on their needs. Markov process models provide a useful tool describing disease progression for life history data. The literature mainly focuses on time homogeneous process. In this paper we develop methods to deal with non-homogeneous Markov process with incomplete clustered life history data. A correlated random effects model is developed to deal with the nonignorable missingness, and a time transformation is employed to address the non-homogeneity in the transition model. Maximum likelihood estimate based on the Monte-Carlo EM algorithm is advocated for parameter estimation. Simulation studies demonstrate that the proposed method works well in many situations. We also apply this method to an Alzheimer's disease study.

Original languageEnglish (US)
Pages (from-to)1-13
Number of pages13
JournalJournal of Multivariate Analysis
Volume117
DOIs
StatePublished - May 1 2013

Fingerprint

Random Effects Model
Markov Process
Markov processes
Monte Carlo EM Algorithm
Transition Model
Alzheimer's Disease
Incomplete Data
Maximum Likelihood Estimate
Progression
Parameter estimation
Process Model
Markov Model
Maximum likelihood
Parameter Estimation
Choose
Simulation Study
Demonstrate
Life
History
Random effects model

Keywords

  • Cluster
  • Markov non-homogeneous
  • Missing not at random
  • Random effects
  • Transition intensity

ASJC Scopus subject areas

  • Statistics and Probability
  • Numerical Analysis
  • Statistics, Probability and Uncertainty

Cite this

A correlated random effects model for non-homogeneous Markov processes with nonignorable missingness. / Chen, Baojiang; Zhou, Xiao Hua.

In: Journal of Multivariate Analysis, Vol. 117, 01.05.2013, p. 1-13.

Research output: Contribution to journalArticle

@article{97291740cb0e43a6ad8028332b90e916,
title = "A correlated random effects model for non-homogeneous Markov processes with nonignorable missingness",
abstract = "Life history data arising in clusters with pre-specified assessment time points for patients often feature incomplete data since patients may choose to visit the clinic based on their needs. Markov process models provide a useful tool describing disease progression for life history data. The literature mainly focuses on time homogeneous process. In this paper we develop methods to deal with non-homogeneous Markov process with incomplete clustered life history data. A correlated random effects model is developed to deal with the nonignorable missingness, and a time transformation is employed to address the non-homogeneity in the transition model. Maximum likelihood estimate based on the Monte-Carlo EM algorithm is advocated for parameter estimation. Simulation studies demonstrate that the proposed method works well in many situations. We also apply this method to an Alzheimer's disease study.",
keywords = "Cluster, Markov non-homogeneous, Missing not at random, Random effects, Transition intensity",
author = "Baojiang Chen and Zhou, {Xiao Hua}",
year = "2013",
month = "5",
day = "1",
doi = "10.1016/j.jmva.2013.01.009",
language = "English (US)",
volume = "117",
pages = "1--13",
journal = "Journal of Multivariate Analysis",
issn = "0047-259X",
publisher = "Academic Press Inc.",

}

TY - JOUR

T1 - A correlated random effects model for non-homogeneous Markov processes with nonignorable missingness

AU - Chen, Baojiang

AU - Zhou, Xiao Hua

PY - 2013/5/1

Y1 - 2013/5/1

N2 - Life history data arising in clusters with pre-specified assessment time points for patients often feature incomplete data since patients may choose to visit the clinic based on their needs. Markov process models provide a useful tool describing disease progression for life history data. The literature mainly focuses on time homogeneous process. In this paper we develop methods to deal with non-homogeneous Markov process with incomplete clustered life history data. A correlated random effects model is developed to deal with the nonignorable missingness, and a time transformation is employed to address the non-homogeneity in the transition model. Maximum likelihood estimate based on the Monte-Carlo EM algorithm is advocated for parameter estimation. Simulation studies demonstrate that the proposed method works well in many situations. We also apply this method to an Alzheimer's disease study.

AB - Life history data arising in clusters with pre-specified assessment time points for patients often feature incomplete data since patients may choose to visit the clinic based on their needs. Markov process models provide a useful tool describing disease progression for life history data. The literature mainly focuses on time homogeneous process. In this paper we develop methods to deal with non-homogeneous Markov process with incomplete clustered life history data. A correlated random effects model is developed to deal with the nonignorable missingness, and a time transformation is employed to address the non-homogeneity in the transition model. Maximum likelihood estimate based on the Monte-Carlo EM algorithm is advocated for parameter estimation. Simulation studies demonstrate that the proposed method works well in many situations. We also apply this method to an Alzheimer's disease study.

KW - Cluster

KW - Markov non-homogeneous

KW - Missing not at random

KW - Random effects

KW - Transition intensity

UR - http://www.scopus.com/inward/record.url?scp=84874517152&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84874517152&partnerID=8YFLogxK

U2 - 10.1016/j.jmva.2013.01.009

DO - 10.1016/j.jmva.2013.01.009

M3 - Article

C2 - 23828666

AN - SCOPUS:84874517152

VL - 117

SP - 1

EP - 13

JO - Journal of Multivariate Analysis

JF - Journal of Multivariate Analysis

SN - 0047-259X

ER -