Mixture multi-state Markov regression model

Amy Ming-Fang Yen, Tony Hsiu-Hsi Chen

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

Although heterogeneity across individuals may be reduced when a two-state process is extended into a multi-state process, the discrepancy between the observed and the predicted for some states may still exist owing to two possibilities, unobserved mixture distribution in the initial state and the effect of measured covariates on subsequent multi-state disease progression. In the present study, we developed a mixture Markov exponential regression model to take account of the above-mentioned heterogeneity across individuals (subject-to-subject variability) with a systematic model selection based on the likelihood ratio test. The model was successfully demonstrated by an empirical example on surveillance of patients with small hepatocellular carcinoma treated by non-surgical methods. The estimated results suggested that the model with the incorporation of unobserved mixture distribution behaves better than the one without. Complete and partial effects regarding risk factors on different subsequent multi-state transitions were identified using a homogeneous Markov model. The combination of both initial mixture distribution and homogeneous Markov exponential regression model makes a significant contribution to reducing heterogeneity across individuals and over time for disease progression.

Original languageEnglish
Pages (from-to)11-21
Number of pages11
JournalJournal of Applied Statistics
Volume34
Issue number1
DOIs
Publication statusPublished - Jan 2007
Externally publishedYes

Fingerprint

Mixture Distribution
Multi-state
Markov Model
Regression Model
Exponential Model
Progression
State Transition
Likelihood Ratio Test
Risk Factors
Model Selection
Surveillance
Discrepancy
Covariates
Partial
Model
Regression model
Mixture distribution

Keywords

  • Markov mixture model
  • Model selection
  • Multi-state

ASJC Scopus subject areas

  • Statistics and Probability

Cite this

Mixture multi-state Markov regression model. / Ming-Fang Yen, Amy; Hsiu-Hsi Chen, Tony.

In: Journal of Applied Statistics, Vol. 34, No. 1, 01.2007, p. 11-21.

Research output: Contribution to journalArticle

Ming-Fang Yen, Amy ; Hsiu-Hsi Chen, Tony. / Mixture multi-state Markov regression model. In: Journal of Applied Statistics. 2007 ; Vol. 34, No. 1. pp. 11-21.
@article{24b9ac1b77c74abc983e17d4fbad5b99,
title = "Mixture multi-state Markov regression model",
abstract = "Although heterogeneity across individuals may be reduced when a two-state process is extended into a multi-state process, the discrepancy between the observed and the predicted for some states may still exist owing to two possibilities, unobserved mixture distribution in the initial state and the effect of measured covariates on subsequent multi-state disease progression. In the present study, we developed a mixture Markov exponential regression model to take account of the above-mentioned heterogeneity across individuals (subject-to-subject variability) with a systematic model selection based on the likelihood ratio test. The model was successfully demonstrated by an empirical example on surveillance of patients with small hepatocellular carcinoma treated by non-surgical methods. The estimated results suggested that the model with the incorporation of unobserved mixture distribution behaves better than the one without. Complete and partial effects regarding risk factors on different subsequent multi-state transitions were identified using a homogeneous Markov model. The combination of both initial mixture distribution and homogeneous Markov exponential regression model makes a significant contribution to reducing heterogeneity across individuals and over time for disease progression.",
keywords = "Markov mixture model, Model selection, Multi-state",
author = "{Ming-Fang Yen}, Amy and {Hsiu-Hsi Chen}, Tony",
year = "2007",
month = "1",
doi = "10.1080/02664760600994711",
language = "English",
volume = "34",
pages = "11--21",
journal = "Journal of Applied Statistics",
issn = "0266-4763",
publisher = "Routledge",
number = "1",

}

TY - JOUR

T1 - Mixture multi-state Markov regression model

AU - Ming-Fang Yen, Amy

AU - Hsiu-Hsi Chen, Tony

PY - 2007/1

Y1 - 2007/1

N2 - Although heterogeneity across individuals may be reduced when a two-state process is extended into a multi-state process, the discrepancy between the observed and the predicted for some states may still exist owing to two possibilities, unobserved mixture distribution in the initial state and the effect of measured covariates on subsequent multi-state disease progression. In the present study, we developed a mixture Markov exponential regression model to take account of the above-mentioned heterogeneity across individuals (subject-to-subject variability) with a systematic model selection based on the likelihood ratio test. The model was successfully demonstrated by an empirical example on surveillance of patients with small hepatocellular carcinoma treated by non-surgical methods. The estimated results suggested that the model with the incorporation of unobserved mixture distribution behaves better than the one without. Complete and partial effects regarding risk factors on different subsequent multi-state transitions were identified using a homogeneous Markov model. The combination of both initial mixture distribution and homogeneous Markov exponential regression model makes a significant contribution to reducing heterogeneity across individuals and over time for disease progression.

AB - Although heterogeneity across individuals may be reduced when a two-state process is extended into a multi-state process, the discrepancy between the observed and the predicted for some states may still exist owing to two possibilities, unobserved mixture distribution in the initial state and the effect of measured covariates on subsequent multi-state disease progression. In the present study, we developed a mixture Markov exponential regression model to take account of the above-mentioned heterogeneity across individuals (subject-to-subject variability) with a systematic model selection based on the likelihood ratio test. The model was successfully demonstrated by an empirical example on surveillance of patients with small hepatocellular carcinoma treated by non-surgical methods. The estimated results suggested that the model with the incorporation of unobserved mixture distribution behaves better than the one without. Complete and partial effects regarding risk factors on different subsequent multi-state transitions were identified using a homogeneous Markov model. The combination of both initial mixture distribution and homogeneous Markov exponential regression model makes a significant contribution to reducing heterogeneity across individuals and over time for disease progression.

KW - Markov mixture model

KW - Model selection

KW - Multi-state

UR - http://www.scopus.com/inward/record.url?scp=33845947914&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33845947914&partnerID=8YFLogxK

U2 - 10.1080/02664760600994711

DO - 10.1080/02664760600994711

M3 - Article

VL - 34

SP - 11

EP - 21

JO - Journal of Applied Statistics

JF - Journal of Applied Statistics

SN - 0266-4763

IS - 1

ER -