mixAR: Mixture Autoregressive Models

Model time series using mixture autoregressive (MAR) models. Implemented are frequentist (EM) and Bayesian methods for estimation, prediction and model evaluation. See Wong and Li (2002) <doi:10.1111/1467-9868.00222>, Boshnakov (2009) <doi:10.1016/j.spl.2009.04.009>), and the extensive references in the documentation.

Version: 0.22.8
Depends: R (≥ 3.5), methods
Imports: stats, graphics, utils, stats4, BB, combinat, timeDate, fGarch, Rdpack (≥ 0.7), gbutils (≥ 0.3-1), MCMCpack, e1071, permute, mvtnorm
Suggests: fma, testthat, covr
Published: 2023-12-19
Author: Georgi N. Boshnakov [aut, cre], Davide Ravagli [aut]
Maintainer: Georgi N. Boshnakov <georgi.boshnakov at manchester.ac.uk>
BugReports: https://github.com/GeoBosh/mixAR/issues
License: GPL-2 | GPL-3 [expanded from: GPL (≥ 2)]
URL: https://geobosh.github.io/mixAR/ (doc), https://github.com/GeoBosh/mixAR/ (devel)
NeedsCompilation: no
Materials: README NEWS
In views: TimeSeries
CRAN checks: mixAR results

Documentation:

Reference manual: mixAR.pdf

Downloads:

Package source: mixAR_0.22.8.tar.gz
Windows binaries: r-devel: mixAR_0.22.8.zip, r-release: mixAR_0.22.8.zip, r-oldrel: mixAR_0.22.8.zip
macOS binaries: r-release (arm64): mixAR_0.22.8.tgz, r-oldrel (arm64): mixAR_0.22.8.tgz, r-release (x86_64): mixAR_0.22.8.tgz
Old sources: mixAR archive

Linking:

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