Bayesian measurement-error-driven hidden Markov regression model for calibrating the effect of covariates on multistate outcomes: Application to androgenetic alopecia

Amy Ming Fang Yen, Hsiu Hsi Chen

Research output: Contribution to journalArticle

Abstract

Multistate Markov regression models used for quantifying the effect size of state-specific covariates pertaining to the dynamics of multistate outcomes have gained popularity. However, the measurements of multistate outcome are prone to the errors of classification, particularly when a population-based survey/research is involved with proxy measurements of outcome due to cost consideration. Such a misclassification may affect the effect size of relevant covariates such as odds ratio used in the field of epidemiology. We proposed a Bayesian measurement-error-driven hidden Markov regression model for calibrating these biased estimates with and without a 2-stage validation design. A simulation algorithm was developed to assess various scenarios of underestimation and overestimation given nondifferential misclassification (independent of covariates) and differential misclassification (dependent on covariates). We applied our proposed method to the community-based survey of androgenetic alopecia and found that the effect size of the majority of covariate was inflated after calibration regardless of which type of misclassification. Our proposed Bayesian measurement-error-driven hidden Markov regression model is practicable and effective in calibrating the effects of covariates on multistate outcome, but the prior distribution on measurement errors accrued from 2-stage validation design is strongly recommended.

Original languageEnglish
Pages (from-to)3125-3146
Number of pages22
JournalStatistics in Medicine
Volume37
Issue number21
DOIs
Publication statusPublished - Sep 20 2018

Fingerprint

Multi-state
Alopecia
Measurement Error
Markov Model
Covariates
Regression Model
Misclassification
Effect Size
Proxy
Calibration
Epidemiology
Odds Ratio
Costs and Cost Analysis
Research
Population
Prior distribution
Biased
Surveys and Questionnaires
Scenarios
Dependent

Keywords

  • Bayesian
  • calibration
  • hidden Markov model
  • Markov regression model
  • measurement error

ASJC Scopus subject areas

  • Epidemiology
  • Statistics and Probability

Cite this

@article{658fcd8881bf44f4bfb04f40611a8d75,
title = "Bayesian measurement-error-driven hidden Markov regression model for calibrating the effect of covariates on multistate outcomes: Application to androgenetic alopecia",
abstract = "Multistate Markov regression models used for quantifying the effect size of state-specific covariates pertaining to the dynamics of multistate outcomes have gained popularity. However, the measurements of multistate outcome are prone to the errors of classification, particularly when a population-based survey/research is involved with proxy measurements of outcome due to cost consideration. Such a misclassification may affect the effect size of relevant covariates such as odds ratio used in the field of epidemiology. We proposed a Bayesian measurement-error-driven hidden Markov regression model for calibrating these biased estimates with and without a 2-stage validation design. A simulation algorithm was developed to assess various scenarios of underestimation and overestimation given nondifferential misclassification (independent of covariates) and differential misclassification (dependent on covariates). We applied our proposed method to the community-based survey of androgenetic alopecia and found that the effect size of the majority of covariate was inflated after calibration regardless of which type of misclassification. Our proposed Bayesian measurement-error-driven hidden Markov regression model is practicable and effective in calibrating the effects of covariates on multistate outcome, but the prior distribution on measurement errors accrued from 2-stage validation design is strongly recommended.",
keywords = "Bayesian, calibration, hidden Markov model, Markov regression model, measurement error",
author = "Yen, {Amy Ming Fang} and Chen, {Hsiu Hsi}",
note = "{\circledC} 2018 The Authors. Statistics in Medicine published by John Wiley & Sons Ltd.",
year = "2018",
month = "9",
day = "20",
doi = "10.1002/sim.7813",
language = "English",
volume = "37",
pages = "3125--3146",
journal = "Statistics in Medicine",
issn = "0277-6715",
publisher = "John Wiley and Sons Ltd",
number = "21",

}

TY - JOUR

T1 - Bayesian measurement-error-driven hidden Markov regression model for calibrating the effect of covariates on multistate outcomes

T2 - Application to androgenetic alopecia

AU - Yen, Amy Ming Fang

AU - Chen, Hsiu Hsi

N1 - © 2018 The Authors. Statistics in Medicine published by John Wiley & Sons Ltd.

PY - 2018/9/20

Y1 - 2018/9/20

N2 - Multistate Markov regression models used for quantifying the effect size of state-specific covariates pertaining to the dynamics of multistate outcomes have gained popularity. However, the measurements of multistate outcome are prone to the errors of classification, particularly when a population-based survey/research is involved with proxy measurements of outcome due to cost consideration. Such a misclassification may affect the effect size of relevant covariates such as odds ratio used in the field of epidemiology. We proposed a Bayesian measurement-error-driven hidden Markov regression model for calibrating these biased estimates with and without a 2-stage validation design. A simulation algorithm was developed to assess various scenarios of underestimation and overestimation given nondifferential misclassification (independent of covariates) and differential misclassification (dependent on covariates). We applied our proposed method to the community-based survey of androgenetic alopecia and found that the effect size of the majority of covariate was inflated after calibration regardless of which type of misclassification. Our proposed Bayesian measurement-error-driven hidden Markov regression model is practicable and effective in calibrating the effects of covariates on multistate outcome, but the prior distribution on measurement errors accrued from 2-stage validation design is strongly recommended.

AB - Multistate Markov regression models used for quantifying the effect size of state-specific covariates pertaining to the dynamics of multistate outcomes have gained popularity. However, the measurements of multistate outcome are prone to the errors of classification, particularly when a population-based survey/research is involved with proxy measurements of outcome due to cost consideration. Such a misclassification may affect the effect size of relevant covariates such as odds ratio used in the field of epidemiology. We proposed a Bayesian measurement-error-driven hidden Markov regression model for calibrating these biased estimates with and without a 2-stage validation design. A simulation algorithm was developed to assess various scenarios of underestimation and overestimation given nondifferential misclassification (independent of covariates) and differential misclassification (dependent on covariates). We applied our proposed method to the community-based survey of androgenetic alopecia and found that the effect size of the majority of covariate was inflated after calibration regardless of which type of misclassification. Our proposed Bayesian measurement-error-driven hidden Markov regression model is practicable and effective in calibrating the effects of covariates on multistate outcome, but the prior distribution on measurement errors accrued from 2-stage validation design is strongly recommended.

KW - Bayesian

KW - calibration

KW - hidden Markov model

KW - Markov regression model

KW - measurement error

UR - http://www.scopus.com/inward/record.url?scp=85051426642&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85051426642&partnerID=8YFLogxK

U2 - 10.1002/sim.7813

DO - 10.1002/sim.7813

M3 - Article

C2 - 29785802

AN - SCOPUS:85051426642

VL - 37

SP - 3125

EP - 3146

JO - Statistics in Medicine

JF - Statistics in Medicine

SN - 0277-6715

IS - 21

ER -