Package: mhsmm
Type: Package
Title: Parameter estimation and prediction for hidden Markov and
        semi-Markov models for data with multiple observation sequences
Version: 0.2.3
Date: 2009-01-21
Author: Jared O'Connell <jared.oconnell@ferring.com>, Soren Hojsgaard
        <sorenh@agrsci.dk>
Maintainer: Jared O'Connell <jared.oconnell@ferring.com>
Description: Parameter estimation and prediction for hidden Markov and
        semi-Markov models for data with multiple observation
        sequences. The times must be equidistant but missing values of
        the observables are allowed. The observables are allowed to be
        multivariate. It is possible to have multiple sequences of
        data. Estimation of the parameters of the models are made using
        EM--algorithms. Computationally demanding parts of the
        algorithm are implemented in C for performance. Finally, the
        package is designed to allow users to specify their own
        emission distributions, giving flexibility in the type of data
        that may be analysed.
License: GPL (>= 2)
LazyLoad: yes
Depends: mvtnorm
Packaged: 2009-04-05 10:16:51 UTC; jared
Repository: CRAN
Date/Publication: 2009-04-14 17:32:17
