CerioliOutlierDetection {CerioliOutlierDetection}R Documentation

CerioliOutlierDetection: package for implementing the Iterated Reweighted MCD outlier detection method of Cerioli (2010)

Description

Implements the outlier detection methodology of Cerioli (2010) based on Mahalanobis distances and the minimum covariance determinant (MCD) estimate of dispersion. Also provides critical values for testing outlyingness of MCD-based Mahalanobis distances using the distribution approximations developed by Hardin and Rocke (2005) and Green and Martin (2014).

Details

The function cerioli2010.irmcd.test() provides the outlier detection methodology of Cerioli (2010), and is probably the best place for a new user of this package to start. See the documentation for that function for examples.

This package was also used to produce the results presented in Green and Martin (2014). There is a companion R package, HardinRockeExtension, that provides code that can be used to replicate the results of that paper. The package HardinRockeExtension is available from Christopher G. Green's GitHub: https://github.com/christopherggreen/HardinRockeExtensionSimulations .

Author(s)

Written and maintained by Christopher G. Green <christopher.g.green@gmail.com>, with advice and support from Doug Martin.

References

Andrea Cerioli. Multivariate outlier detection with high-breakdown estimators. Journal of the American Statistical Association, 105(489):147-156, 2010. doi:10.1198/jasa.2009.tm09147

C. G. Green and R. Douglas Martin. An extension of a method of Hardin and Rocke, with an application to multivariate outlier detection via the IRMCD method of Cerioli. Working Paper, 2017. Available from https://christopherggreen.github.io/papers/hr05_extension.pdf

J. Hardin and D. M. Rocke. The distribution of robust distances. Journal of Computational and Graphical Statistics, 14:928-946, 2005. doi:10.1198/106186005X77685


[Package CerioliOutlierDetection version 1.1.13 Index]