svpChange: Smallest Valid Partitioning for Change-Point Detection

Provides methods for detecting multiple change-points and segmenting univariate time series using Smallest Valid Partitioning (SVP). SVP searches for a partition with the smallest number of segments whose segments satisfy a user-defined or built-in validity test. Among partitions with the same number of segments, it minimizes a within-segment sum-of-squared-errors criterion.

Version: 0.2.0
Imports: Rcpp (≥ 1.0.10), stats
LinkingTo: Rcpp, RcppArmadillo
Suggests: stepR, testthat (≥ 3.0.0)
Published: 2026-09-30
DOI: 10.32614/CRAN.package.svpChange (may not be active yet)
Author: Vincent Runge [aut, cre, cph], Alexandre Combeau [aut], Gaetano Romano [aut], Anica Kostic [ctb]
Maintainer: Vincent Runge <vincent.runge at univ-evry.fr>
BugReports: https://github.com/vrunge/svpChange/issues
License: GPL-3
URL: https://github.com/vrunge/svpChange
NeedsCompilation: yes
Materials: README
CRAN checks: svpChange results

Documentation:

Reference manual: svpChange.html , svpChange.pdf

Downloads:

Package source: svpChange_0.2.0.tar.gz
Windows binaries: r-devel: svpChange_0.2.0.zip, r-release: not available, r-oldrel: not available
macOS binaries: r-release (arm64): not available, r-oldrel (arm64): not available, r-release (x86_64): svpChange_0.2.0.tgz, r-oldrel (x86_64): svpChange_0.2.0.tgz

Linking:

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