Open AccessSoftware Tools for Robust Analysis of High-Dimensional Data
Author(s) -
Valentin Todorov,
Peter Filzmoser
Publication year - 2014
Publication title -
österreichische zeitschrift für statistik
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.342
H-Index - 9
ISSN - 1026-597X
DOI - 10.17713/ajs.v43i4.44
Subject(s) - computer science , outlier , scope (computer science) , robust regression , r package , principal (computer security) , interface (matter) , software , principal component analysis , multivariate statistics , software package , data mining , computational statistics , least squares function approximation , algorithm , artificial intelligence , mathematics , machine learning , statistics , programming language , parallel computing , bubble , maximum bubble pressure method , estimator , operating system
The present work discusses robust multivariate methods specifically designed for highdimensions. Their implementation in R is presented and their application is illustratedon examples. The first group are algorithms for outlier detection, already introducedelsewhere and implemented in other packages. The value added of the new package isthat all methods follow the same design pattern and thus can use the same graphicaland diagnostic tools. The next topic covered is sparse principal components including anobject oriented interface to the standard method proposed by Zou, Hastie, and Tibshirani(2006) and the robust one proposed by Croux, Filzmoser, and Fritz (2013). Robust partialleast squares (see Hubert and Vanden Branden 2003) as well as partial least squares fordiscriminant analysis conclude the scope of the new package.