watson: Fitting and Simulating Mixtures of Watson Distributions

Tools for fitting and simulating mixtures of Watson distributions. The random sampling scheme of the package offers two sampling algorithms that are based of the results of Sablica, Hornik and Leydold (2022) <https://research.wu.ac.at/en/publications/random-sampling-from-the-watson-distribution>. What is more, the package offers a smart tool to combine these two methods, and based on the selected parameters, it approximates the relative sampling speed for both methods and picks the faster one. In addition, the package offers a fitting function for the mixtures of Watson distribution, that uses the expectation-maximization (EM) algorithm. Special features are the possibility to use multiple variants of the E-step and M-step, sparse matrices for the data representation and state of the art methods for numerical evaluation of needed special functions using the results of Sablica and Hornik (2022) <https://www.ams.org/journals/mcom/2022-91-334/S0025-5718-2021-03690-X/>.

Version: 0.4
Depends: R (≥ 3.1.0)
Imports: Rcpp (≥ 0.12.18), Tinflex (≥ 1.8)
LinkingTo: Rcpp, RcppArmadillo, Tinflex
Published: 2023-06-01
DOI: 10.32614/CRAN.package.watson
Author: Lukas Sablica ORCID iD [aut, cre], Kurt Hornik ORCID iD [aut], Josef Leydold ORCID iD [aut], Gerard Jungman [ctb, cph] (Author and copyright holder of included GNU GSL code), Brian Gough [ctb, cph] (Author and copyright holder of included GNU GSL code)
Maintainer: Lukas Sablica <lsablica at wu.ac.at>
License: GPL-3
NeedsCompilation: yes
Materials: NEWS
In views: Distributions
CRAN checks: watson results


Reference manual: watson.pdf


Package source: watson_0.4.tar.gz
Windows binaries: r-devel: watson_0.4.zip, r-release: watson_0.4.zip, r-oldrel: watson_0.4.zip
macOS binaries: r-release (arm64): watson_0.4.tgz, r-oldrel (arm64): watson_0.4.tgz, r-release (x86_64): watson_0.4.tgz, r-oldrel (x86_64): watson_0.4.tgz
Old sources: watson archive


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