A Bayesian Approach in Estimating Transition Probabilities of a Discrete-time Markov Chain for Ignorable Intermittent Missing Data

Junsheng Ma, Xiaoying Yu, Elaine Symanski, Rachelle Doody, Wenyaw Chan

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

This article focuses on data analyses under the scenario of missing at random within discrete-time Markov chain models. The naive method, nonlinear (NL) method, and Expectation-Maximization (EM) algorithm are discussed. We extend the NL method into a Bayesian framework, using an adjusted rejection algorithm to sample the posterior distribution, and estimating the transition probabilities with a Monte Carlo algorithm. We compare the Bayesian nonlinear (BNL) method with the naive method and the EM algorithm with various missing rates, and comprehensively evaluate estimators in terms of biases, variances, mean square errors, and coverage probabilities (CPs). Our simulation results show that the EM algorithm usually offers smallest variances but with poorest CP, while the BNL method has smaller variances and better/similar CP as compared to the naive method. When the missing rate is low (about 9%, MAR), the three methods are comparable. Whereas when the missing rate is high (about 25%, MAR), overall, the BNL method performs slightly but consistently better than the naive method regarding variances and CP. Data from a longitudinal study of stress level among caregivers of individuals with Alzheimer’s disease is used to illustrate these methods.

Original languageEnglish (US)
Pages (from-to)2598-2616
Number of pages19
JournalCommunications in Statistics: Simulation and Computation
Volume45
Issue number7
DOIs
StatePublished - Aug 8 2016
Externally publishedYes

Fingerprint

Missing Data
Transition Probability
Bayesian Approach
Markov processes
Markov chain
Discrete-time
Coverage Probability
Expectation-maximization Algorithm
Mars
Mean square error
Missing at Random
Alzheimer's Disease
Markov Chain Model
Longitudinal Study
Monte Carlo Algorithm
Error Probability
Posterior distribution
Rejection
Estimator
Scenarios

Keywords

  • Bayesian
  • EM algorithm
  • Markov chain
  • Missing data
  • Rejection algorithm

ASJC Scopus subject areas

  • Statistics and Probability
  • Modeling and Simulation

Cite this

A Bayesian Approach in Estimating Transition Probabilities of a Discrete-time Markov Chain for Ignorable Intermittent Missing Data. / Ma, Junsheng; Yu, Xiaoying; Symanski, Elaine; Doody, Rachelle; Chan, Wenyaw.

In: Communications in Statistics: Simulation and Computation, Vol. 45, No. 7, 08.08.2016, p. 2598-2616.

Research output: Contribution to journalArticle

@article{d0f8a2dc49a54421a6faa149b773495d,
title = "A Bayesian Approach in Estimating Transition Probabilities of a Discrete-time Markov Chain for Ignorable Intermittent Missing Data",
abstract = "This article focuses on data analyses under the scenario of missing at random within discrete-time Markov chain models. The naive method, nonlinear (NL) method, and Expectation-Maximization (EM) algorithm are discussed. We extend the NL method into a Bayesian framework, using an adjusted rejection algorithm to sample the posterior distribution, and estimating the transition probabilities with a Monte Carlo algorithm. We compare the Bayesian nonlinear (BNL) method with the naive method and the EM algorithm with various missing rates, and comprehensively evaluate estimators in terms of biases, variances, mean square errors, and coverage probabilities (CPs). Our simulation results show that the EM algorithm usually offers smallest variances but with poorest CP, while the BNL method has smaller variances and better/similar CP as compared to the naive method. When the missing rate is low (about 9{\%}, MAR), the three methods are comparable. Whereas when the missing rate is high (about 25{\%}, MAR), overall, the BNL method performs slightly but consistently better than the naive method regarding variances and CP. Data from a longitudinal study of stress level among caregivers of individuals with Alzheimer’s disease is used to illustrate these methods.",
keywords = "Bayesian, EM algorithm, Markov chain, Missing data, Rejection algorithm",
author = "Junsheng Ma and Xiaoying Yu and Elaine Symanski and Rachelle Doody and Wenyaw Chan",
year = "2016",
month = "8",
day = "8",
doi = "10.1080/03610918.2014.911895",
language = "English (US)",
volume = "45",
pages = "2598--2616",
journal = "Communications in Statistics Part B: Simulation and Computation",
issn = "0361-0918",
publisher = "Taylor and Francis Ltd.",
number = "7",

}

TY - JOUR

T1 - A Bayesian Approach in Estimating Transition Probabilities of a Discrete-time Markov Chain for Ignorable Intermittent Missing Data

AU - Ma, Junsheng

AU - Yu, Xiaoying

AU - Symanski, Elaine

AU - Doody, Rachelle

AU - Chan, Wenyaw

PY - 2016/8/8

Y1 - 2016/8/8

N2 - This article focuses on data analyses under the scenario of missing at random within discrete-time Markov chain models. The naive method, nonlinear (NL) method, and Expectation-Maximization (EM) algorithm are discussed. We extend the NL method into a Bayesian framework, using an adjusted rejection algorithm to sample the posterior distribution, and estimating the transition probabilities with a Monte Carlo algorithm. We compare the Bayesian nonlinear (BNL) method with the naive method and the EM algorithm with various missing rates, and comprehensively evaluate estimators in terms of biases, variances, mean square errors, and coverage probabilities (CPs). Our simulation results show that the EM algorithm usually offers smallest variances but with poorest CP, while the BNL method has smaller variances and better/similar CP as compared to the naive method. When the missing rate is low (about 9%, MAR), the three methods are comparable. Whereas when the missing rate is high (about 25%, MAR), overall, the BNL method performs slightly but consistently better than the naive method regarding variances and CP. Data from a longitudinal study of stress level among caregivers of individuals with Alzheimer’s disease is used to illustrate these methods.

AB - This article focuses on data analyses under the scenario of missing at random within discrete-time Markov chain models. The naive method, nonlinear (NL) method, and Expectation-Maximization (EM) algorithm are discussed. We extend the NL method into a Bayesian framework, using an adjusted rejection algorithm to sample the posterior distribution, and estimating the transition probabilities with a Monte Carlo algorithm. We compare the Bayesian nonlinear (BNL) method with the naive method and the EM algorithm with various missing rates, and comprehensively evaluate estimators in terms of biases, variances, mean square errors, and coverage probabilities (CPs). Our simulation results show that the EM algorithm usually offers smallest variances but with poorest CP, while the BNL method has smaller variances and better/similar CP as compared to the naive method. When the missing rate is low (about 9%, MAR), the three methods are comparable. Whereas when the missing rate is high (about 25%, MAR), overall, the BNL method performs slightly but consistently better than the naive method regarding variances and CP. Data from a longitudinal study of stress level among caregivers of individuals with Alzheimer’s disease is used to illustrate these methods.

KW - Bayesian

KW - EM algorithm

KW - Markov chain

KW - Missing data

KW - Rejection algorithm

UR - http://www.scopus.com/inward/record.url?scp=84975299940&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84975299940&partnerID=8YFLogxK

U2 - 10.1080/03610918.2014.911895

DO - 10.1080/03610918.2014.911895

M3 - Article

VL - 45

SP - 2598

EP - 2616

JO - Communications in Statistics Part B: Simulation and Computation

JF - Communications in Statistics Part B: Simulation and Computation

SN - 0361-0918

IS - 7

ER -