A cautionary note on robust covariance plug-in methods

Abstract

Many multivariate statistical methods rely heavily on the sample covariance matrix. It is well known though that the sample covariance matrix is highly non-robust. One popular alternative approach for "robustifying" the multivariate method is to simply replace the role of the covariance matrix with some robust scatter matrix. The aim of this paper is to point out that in some situations certain properties of the covariance matrix are needed for the corresponding robust "plug-in" method to be a valid approach, and that not all scatter matrices necessarily possess these important properties. In particular, the following three multivariate methods are discussed in this paper: independent components analysis, observational regression and graphical modeling. For each case, it is shown that using a symmetrized robust scatter matrix in place of the covariance matrix results in a proper robust multivariate method.

24 pages, 7 figures

References in corpus (2)

• Robust graphical modeling of gene networks using classical and alternative T-distributions
• Elliptical graphical modelling

Cited by in corpus (15)

• An Overview of Robust Subspace Recovery
• ICS for Multivariate Outlier Detection with Application to Quality Control
• Asymptotic and bootstrap tests for subspace dimension
• Robust Sparse Covariance Estimation by Thresholding Tyler's M-Estimator
• New Algorithms for $M$-Estimation of Multivariate Scatter and Location
• Extracting conditionally heteroscedastic components using ICA
• Numerical considerations and a new implementation for ICS
• Tandem clustering with invariant coordinate selection
• Spatial Blind Source Separation in the Presence of a Drift
• Non-Gaussian component analysis: testing the dimension of the signal subspace
• Approximating Symmetrized Estimators of Scatter via Balanced Incomplete U-Statistics
• On characterizations of the covariance matrix
• Gini Covariance Matrix and its Affine Equivariant Version
• Invariant Coordinate Selection and Fisher discriminant subspace beyond the case of two groups
• A method for sparse and robust independent component analysis