Robustifying principal component analysis with spatial sign vectors



: Taskinen S, Koch I, Oja H

Publisher: ELSEVIER SCIENCE BV

: 2012

: Statistics and Probability Letters

: STATISTICS & PROBABILITY LETTERS

: STAT PROBABIL LETT

: 82

: 4

: 765

: 774

: 10

: 0167-7152

DOI: https://doi.org/10.1016/j.spl.2012.01.001


In this paper, we apply orthogonally equivariant spatial sign covariance matrices as well as their affine equivariant counterparts in principal component analysis. The influence functions and asymptotic covariance matrices of eigenvectors based on robust covariance estimators are derived in order to compare the robustness and efficiency properties. We show in particular that the estimators that use pairwise differences of the observed data have very good efficiency properties, providing practical robust alternatives to classical sample covariance matrix based methods. (C) 2012 Elsevier B.V. All rights reserved.



Last updated on 2024-26-11 at 18:33