Generalized Infinite Hidden Markov Models

Abstract

We introduce a flexible Bayesian nonparametric hidden Markov model for longitudinal data based on the hidden hierarchical Dirichlet process. Unlike the classical infinite hidden Markov model, the proposed model allows transition probabilities to change over time. In particular, this model provides a framework that operates between homogeneous and heterogeneous Markov model formulations, allowing the rows of the transition probability matrix to be clustered ac- cording to their temporal evolution. Inference is performed through a Markov chain Monte Carlo algorithm, which enables the joint estimation of model parameters, latent variables, and number of states, within a unified framework. Simulation studies under both homogeneous and heterogeneous transition regimes show that the proposed model tends to recover the true latent structure, whereas the infinite hidden Markov model tends to overestimate the number of states when transitions vary over time. Two applications illustrate the ability of the model to detect changes in the transition dynamics.