Bayesian inference in hidden Markov models through the reversible jump Markov chain Monte Carlo method

• 成果类型: Article
• 署名作者: Robert, CP; Rydén, T; Titterington, DM
• 署名单位: Lund University; Institut Polytechnique de Paris; ENSAE Paris; University of Glasgow
• 刊物名称: JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES B-STATISTICAL METHODOLOGY
• ISSN/ISSBN: 1369-7412
• DOI: 10.1111/1467-9868.00219
• 发表日期: 2000
• 页码: 57-75
• 关键词: maximum-likelihood-estimation; posterior distributions; mixture-models; components; series; number

摘要

Hidden Markov models form an extension of mixture models which provides a flexible class of models exhibiting dependence and a possibly large degree of variability. We show how reversible jump Markov chain Monte Carte techniques can be used to estimate the parameters as well as the number of components of a hidden Markov model in a Bayesian framework. We employ a mixture of zero-mean normal distributions as our main example and apply this model to three sets of data from finance, meteorology and geomagnetism.