Finding multivariate outliers with FastPCS

DOI10.1016/J.CSDA.2013.07.021MaRDI QIDQ150316zbMATH OpenOpenAlexFDO

Authors Kaveh Vakili, Eric Schmitt, Kaveh Vakili, Eric Schmitt

Publication date January 2014

Published in Computational Statistics and Data Analysis (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1301.2053, https://lirias.kuleuven.be/handle/123456789/412937

zbMATH Keywords

outlier detectioncomputational statisticsmultivariate statistics

Mathematics Subject Classification ID

Computational methods for problems pertaining to statistics (62-08) Estimation in multivariate analysis (62H12) Robustness and adaptive procedures (parametric inference) (62F35)

Abstract: The Projection Congruent Subset (PCS) Outlyingness is a new index of multivariate outlyingness obtained by considering univariate projections of the data. Like many other outlier detection procedures, PCS searches for a subset which minimizes a criterion. The difference is that the new criterion was designed to be insensitive to the outliers. PCS is supported by FastPCS, a fast and affine equivariant algorithm which we also detail. Both an extensive simulation study and a real data application from the field of engineering show that FastPCS performs better than its competitors.

Recommendations

• The finite sample breakdown point of PCS
• scientific article; zbMATH DE number 4020243
• An iterative method for the detection of multivariate outliers
• Identification of Outliers in Multivariate Data
• A procedure for the detection of multivariate outliers.

Cites work

• scientific article; zbMATH DE number 194744 (Why is no real title available?)
• Identification of Outliers in Multivariate Data
• Lattice. Multivariate data visualization with R
• Robust Statistics
• The maximum bias of robust covariances
• Unconventional features of positive-breakdown estimators

Cited in

(8)

• The finite sample breakdown point of PCS
• FastPCS
• The FastHCS algorithm for robust PCA
• Multivariate Outliers and the O3 Plot
• Robust estimation of (partial) autocorrelation
• Fast calibrations of the forward search for testing multiple outliers in regression
• A Faster Subquadratic Algorithm for Finding Outlier Correlations
• Dimension Reduction for Outlier Detection Using DOBIN

Describes a project that uses

Uses Software

• R
• robustbase
• lattice
• rrcov
• robustX

This page was built for publication: Finding multivariate outliers with FastPCS

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q150316)