Continuous time hidden Markov model for longitudinal data

doi:10.1016/j.jmva.2020.104646

CSpace > 应用数学研究所

	Continuous time hidden Markov model for longitudinal data
	Zhou, Jie 1; Song, Xinyuan 2; Sun, Liuquan3
	2020-09-01
发表期刊	JOURNAL OF MULTIVARIATE ANALYSIS
ISSN	0047-259X
卷号	179 页码:16
摘要	Hidden Markov models (HMMs) describe the relationship between two stochastic processes, namely, an observed outcome process and an unobservable finite-state transition process. Given their ability to model dynamic heterogeneity, HMMs are extensively used to analyze heterogeneous longitudinal data. A majority of early developments in HMMs assume that observation times are discrete and regular. This assumption is often unrealistic in substantive research settings where subjects are intermittently seen and the observation times are continuous or not predetermined. However, available works in this direction restricted only to certain special cases with a homogeneous generating matrix for the Markov process. Moreover, early developments have mainly assumed that the number of hidden states of an HMM is fixed and predetermined based on the knowledge of the subjects or a certain criterion. In this article, we consider a general continuous-time HMM with a covariate specific generating matrix and an unknown number of hidden states. The proposed model is highly flexible, thereby enabling it to accommodate different types of longitudinal data that are regularly, irregularly, or continuously collected. We develop a maximum likelihood approach along with an efficient computer algorithm for parameter estimation. We propose a new penalized procedure to select the number of hidden states. The asymptotic properties of the estimators of the parameters and number of hidden states are established. Various satisfactory features, including the finite sample performance of the proposed methodology, are demonstrated through simulation studies. The application of the proposed model to a dataset of bladder tumors is presented. (C) 2020 Elsevier Inc. All rights reserved.
关键词	Continuous-time HMMs Longitudinal data ML estimator Unknown number of hidden states SCAD penalty
DOI	10.1016/j.jmva.2020.104646
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China[11671275] ; National Natural Science Foundation of China[11471223] ; National Natural Science Foundation of China[11771431] ; National Natural Science Foundation of China[11690015] ; National Natural Science Foundation of China[11926341] ; Key Laboratory of RCSDS, CAS, PR China[2008DP173182] ; Research Grants Council of the Hong Kong Special Administrative Region[14303017] ; Research Grants Council of the Hong Kong Special Administrative Region[14301918] ; Academy for Multidisciplinary Studies of Capital Normal University, PR China
WOS研究方向	Mathematics
WOS类目	Statistics & Probability
WOS记录号	WOS:000552835600011
出版者	ELSEVIER INC
引用统计
文献类型	期刊论文
条目标识符	http://ir.amss.ac.cn/handle/2S8OKBNM/51925
专题	应用数学研究所
通讯作者	Song, Xinyuan
作者单位	1.Capital Normal Univ, Sch Math, Beijing 100048, Peoples R China 2.Chinese Univ Hong Kong, Dept Stat, Shatin, Hong Kong, Peoples R China 3.Chinese Acad Sci, Acad Math & Syst Sci, Inst Appl Math, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Zhou, Jie,Song, Xinyuan,Sun, Liuquan. Continuous time hidden Markov model for longitudinal data[J]. JOURNAL OF MULTIVARIATE ANALYSIS,2020,179:16.
APA	Zhou, Jie,Song, Xinyuan,&Sun, Liuquan.(2020).Continuous time hidden Markov model for longitudinal data.JOURNAL OF MULTIVARIATE ANALYSIS,179,16.
MLA	Zhou, Jie,et al."Continuous time hidden Markov model for longitudinal data".JOURNAL OF MULTIVARIATE ANALYSIS 179(2020):16.