Reversible jump and the label switching problem in hidden Markov models

• Published in: Journal of statistical planning and inference Vol. 139; no. 7; pp. 2305 - 2315
• Main Author: Spezia, Luigi
• Format: Journal Article
• Language: English
• Published: Kidlington Elsevier B.V 01.07.2009; Elsevier
• Subjects: Classification; Clustering; Distribution theory; Exact sciences and technology; General topics; Identifiability; Markov mixture models; Markov processes; Mathematics; Numerical analysis; Numerical analysis. Scientific computation; Numerical methods in probability and statistics; Probability and statistics; Probability theory and stochastic processes; Sciences and techniques of general use; Statistics; Trans-dimensional MCMC; Identifiability; Markov mixture models; Trans-dimensional MCMC; Clustering; Classification; Invariant; Rejection sampling; Statistical distribution; Iteration; Stochastic method; Markov chain; Reversible jump; Approximation theory; Bayes estimation; Mixed distribution; Monte Carlo method; Fitting; Prior distribution; Permutation; Statistical estimation; Statistical decision; Markov model; Gibbs sampling; Algorithm; Statistical method; Numerical analysis; Hidden Markov models; Hidden Markov model

Reversible jump Markov chain Monte Carlo (RJMCMC) algorithms can be efficiently applied in Bayesian inference for hidden Markov models (HMMs), when the number of latent regimes is unknown. As for finite mixture models, when priors are invariant to the relabelling of the regimes, HMMs are unidentifia...