
depmix is a package for fitting multigroup mixtures of latent/hidden Markov
models for arbitrary length multivariate timeseries data of mixed
categorical and continuous variables.  This includes as special cases 
the following models: finite mixtures and latent class models (T=1), the latent
Markov model for univariate and multivariate timeseries, and mixtures of
the latter.  Moreover, it includes the possibility of specifying general
linear constraints between parameters.

Currently, the possible response distributions include the bernouilli,
gaussian (normal), weibull, gamma, and log-normal.  The latter three
distributions have two- and three parameter versions.  Only for the
multinomial and gaussian distributions, exact gradients are implemented.
As a result, computing standard errors for other itemtypes can only be
accomplished with bootstrapping or other approximate methods. 

The sources include the possibility of using NPSOL for model parameter
optimization.




