CDGHMM: Hidden Markov Models for Multivariate Panel Data

Estimates hidden Markov models from the family of Cholesky-decomposed Gaussian hidden Markov models (CDGHMM) under various missingness schemes. This family improves upon estimation of traditional Gaussian HMMs by directly modelling the distinct correlation structures that arise from longitudinal data, as well as, controlling for dropped out observations and non-random missingness. See Neal, Sochaniwsky and McNicholas (2024) <doi:10.48550/arXiv.2404.04122>.

Version: 0.1.0
Depends: R (≥ 3.5.0)
Imports: MASS, mvtnorm, ramify, cluster
Published: 2024-05-16
Author: Mackenzie R. Neal ORCID iD [aut, cre], Alexa A. Sochaniwsky [aut], Paul D. McNicholas ORCID iD [aut]
Maintainer: Mackenzie R. Neal <nealm6 at mcmaster.ca>
License: GPL-2 | GPL-3 [expanded from: GPL (≥ 2)]
NeedsCompilation: no
Citation: CDGHMM citation info
CRAN checks: CDGHMM results

Documentation:

Reference manual: CDGHMM.pdf

Downloads:

Package source: CDGHMM_0.1.0.tar.gz
Windows binaries: r-devel: CDGHMM_0.1.0.zip, r-release: CDGHMM_0.1.0.zip, r-oldrel: CDGHMM_0.1.0.zip
macOS binaries: r-release (arm64): CDGHMM_0.1.0.tgz, r-oldrel (arm64): CDGHMM_0.1.0.tgz, r-release (x86_64): CDGHMM_0.1.0.tgz, r-oldrel (x86_64): CDGHMM_0.1.0.tgz

Linking:

Please use the canonical form https://CRAN.R-project.org/package=CDGHMM to link to this page.