<b>depmixS4</b>: An<i>R</i>Package for Hidden Markov Models

TLDR

The package builds on standard Markov, hidden Markov, latent class, and finite mixture models. depmixS4 provides a general R framework for fitting dependent mixture models to mixed multivariate data using GLM, multinomial, or multivariate normal distributions, with optional extensions, and estimates parameters via EM or numerical optimization (Rsolnp/Rdonlp2).

Abstract

<b>depmixS4</b> implements a general framework for defining and estimating dependent mixture models in the <b>R</b> programming language. This includes standard Markov models, latent/hidden Markov models, and latent class and finite mixture distribution models. The models can be fitted on mixed multivariate data with distributions from the <b>glm</b> family, the (logistic) multinomial, or the multivariate normal distribution. Other distributions can be added easily, and an example is provided with the <i>exgaus</i> distribution. Parameters are estimated by the expectation-maximization (EM) algorithm or, when (linear) constraints are imposed on the parameters, by direct numerical optimization with the <b>Rsolnp</b> or <b>Rdonlp2</b> routines.