An implementation of Bayesian online changepoint detection (Adams and MacKay (2007) <doi:10.48550/arXiv.0710.3742>) with an option for probability based outlier detection and removal (Wendelberger et. al. (2021) <doi:10.48550/arXiv.2112.12899>). Building on the independent multivariate constant mean model implemented in the 'R' package 'ocp', this package models multivariate data as multivariate normal about a linear trend, defined by user input covariates, with an unstructured error covariance. Changepoints are identified based on a probability threshold for windows of points.
Version: | 1.2 |
Depends: | R (≥ 3.5.0), methods |
Imports: | Rcpp (≥ 1.0.7), RcppArmadillo |
LinkingTo: | Rcpp, RcppArmadillo, RcppDist |
Suggests: | mvtnorm |
Published: | 2023-12-13 |
DOI: | 10.32614/CRAN.package.roboBayes |
Author: | Laura Wendelberger [aut], Josh Gray [aut], Brian Reich [aut], Alyson Wilson [aut], Shannon T. Holloway [aut, cre] |
Maintainer: | Shannon T. Holloway <shannon.t.holloway at gmail.com> |
License: | GPL-2 |
NeedsCompilation: | yes |
Materials: | NEWS |
CRAN checks: | roboBayes results |
Reference manual: | roboBayes.pdf |
Package source: | roboBayes_1.2.tar.gz |
Windows binaries: | r-devel: roboBayes_1.2.zip, r-release: roboBayes_1.2.zip, r-oldrel: roboBayes_1.2.zip |
macOS binaries: | r-release (arm64): roboBayes_1.2.tgz, r-oldrel (arm64): roboBayes_1.2.tgz, r-release (x86_64): roboBayes_1.2.tgz, r-oldrel (x86_64): roboBayes_1.2.tgz |
Old sources: | roboBayes archive |
Please use the canonical form https://CRAN.R-project.org/package=roboBayes to link to this page.