npcp: Some Nonparametric Tests for Change-Point Detection in Possibly Multivariate Observations

Provides nonparametric tests for assessing whether possibly serially dependent univariate or multivariate observations have the same c.d.f. or not. In addition to tests focusing directly on the c.d.f., the package contains tests designed to be particularly sensitive to changes in the underlying copula, Spearman's rho or certain quantities that can be estimated using one-sample U-statistics of order two such as the variance, Gini's mean difference or Kendall's tau. The latest addition is a nonparametric test for detecting changes in the distribution of independent block maxima.

Version: 0.1-6
Imports: stats
Suggests: copula
Published: 2015-07-24
Author: Ivan Kojadinovic
Maintainer: Ivan Kojadinovic <ivan.kojadinovic at univ-pau.fr>
License: GPL (≥ 3) | file LICENCE
NeedsCompilation: yes
CRAN checks: npcp results

Downloads:

Reference manual: npcp.pdf
Package source: npcp_0.1-6.tar.gz
Windows binaries: r-devel: npcp_0.1-6.zip, r-release: npcp_0.1-6.zip, r-oldrel: npcp_0.1-6.zip
OS X El Capitan binaries: r-release: npcp_0.1-6.tgz
OS X Mavericks binaries: r-oldrel: npcp_0.1-6.tgz
Old sources: npcp archive

Linking:

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