Bayesian inference for Hidden Markov Model

 Hidden Markov Models can be considered an extension of mixture models, allowing fordependent observations. In a hierarchical Bayesian framework, we show how ReversibleJump Markov Chain Monte Carlo techniques can be used to estimate the parameters of amodel, as well as the number of regimes. We consider a mixture of normal distributionscharacterized by different means and variances under each regime, extending the modelproposed by Robert <font size="2">et al. </font><font size="2">(2000), based on a mixture of zero mean normal distributions.</font>