Dirichlet process hidden Markov multiple change-point model
Publication in refereed journal


香港中文大学研究人员 ( 现职)

庄太量教授 (经济学系)

全文

数位物件识别号 (DOI) http://dx.doi.org/10.1214/14-BA910

引用次数
Web of Sciencehttp://aims.cuhk.edu.hk/converis/portal/Publication/0WOS source URL
Scopushttp://aims.cuhk.edu.hk/converis/portal/Publication/1Scopus source URL

其它资讯

摘要This paper proposes a new Bayesian multiple change-point model which is based on the hidden Markov approach. The Dirichlet process hidden Markov model does not require the specification of the number of change-points a priori. Hence our model is robust to model specification in contrast to the fully parametric Bayesian model. We propose a general Markov chain Monte Carlo algorithm which only needs to sample the states around change-points. Simulations for a normal mean-shift model with known and unknown variance demonstrate advantages of our approach. Two applications, namely the coal-mining disaster data and the real United States Gross Domestic Product growth, are provided. We detect a single change-point for both the disaster data and US GDP growth. All the change-point locations and posterior inferences of the two applications are in line with existing methods.

着者Ko S.I.M., Chong T.T.L., Ghosh P.
期刊名称Bayesian Analysis
出版年份2http://aims.cuhk.edu.hk/converis/portal/Publication/0http://aims.cuhk.edu.hk/converis/portal/Publication/15
月份http://aims.cuhk.edu.hk/converis/portal/Publication/1
日期http://aims.cuhk.edu.hk/converis/portal/Publication/1
卷号http://aims.cuhk.edu.hk/converis/portal/Publication/1http://aims.cuhk.edu.hk/converis/portal/Publication/0
期次2
出版社Carnegie Mellon University
出版地United States
页次275 - 296
国际标準期刊号http://aims.cuhk.edu.hk/converis/portal/Publication/1936-http://aims.cuhk.edu.hk/converis/portal/Publication/0975
语言英式英语

关键词Change-point, Dirichlet process, Hidden markov model, Markov chain monte carlo, Nonparametric bayesian