ICSOutlier: Outlier Detection Using Invariant Coordinate Selection

Multivariate outlier detection is performed using invariant coordinates where the package offers different methods to choose the appropriate components. ICS is a general multivariate technique with many applications in multivariate analysis. ICSOutlier offers a selection of functions for automated detection of outliers in the data based on a fitted ICS object or by specifying the dataset and the scatters of interest. The current implementation targets data sets with only a small percentage of outliers.

Version:	0.4-1
Depends:	R (≥ 3.0.0), methods, ICS (≥ 1.4-0), moments
Imports:	graphics, grDevices, mvtnorm, parallel
Suggests:	ICSClust, REPPlab, testthat (≥ 3.0.0)
Published:	2025-08-28
DOI:	10.32614/CRAN.package.ICSOutlier
Author:	Klaus Nordhausen [aut, cre], Aurore Archimbaud [aut], Anne Ruiz-Gazen [aut]
Maintainer:	Klaus Nordhausen <klausnordhausenR at gmail.com>
License:	GPL-2 | GPL-3 [expanded from: GPL (≥ 2)]
NeedsCompilation:	no
Citation:	ICSOutlier citation info
Materials:	NEWS
In views:	AnomalyDetection
CRAN checks:	ICSOutlier results

Documentation:

Reference manual:

ICSOutlier.html , ICSOutlier.pdf

Downloads:

Package source:	ICSOutlier_0.4-1.tar.gz
Windows binaries:	r-devel: ICSOutlier_0.4-1.zip, r-release: ICSOutlier_0.4-1.zip, r-oldrel: ICSOutlier_0.4-1.zip
macOS binaries:	r-release (arm64): ICSOutlier_0.4-1.tgz, r-oldrel (arm64): ICSOutlier_0.4-1.tgz, r-release (x86_64): ICSOutlier_0.4-1.tgz, r-oldrel (x86_64): ICSOutlier_0.4-1.tgz
Old sources:	ICSOutlier archive

Reverse dependencies:

Reverse depends:	ICSShiny
Reverse suggests:	ICS, performance

Linking:

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