The K-Step Spatial Sign Covariance Matrix

C. Croux; C. Dehon; A. Yadine

The K-Step Spatial Sign Covariance Matrix

C. Croux, C. Dehon, A. Yadine

Research output: Working paper › Discussion paper › Other research output

11 Citations (Scopus)

270 Downloads (Pure)

Abstract

The Sign Covariance Matrix is an orthogonal equivariant estimator of mul- tivariate scale. It is often used as an easy-to-compute and highly robust estimator. In this paper we propose a k-step version of the Sign Covariance Matrix, which improves its e±ciency while keeping the maximal breakdown point. If k tends to infinity, Tyler's M-estimator is obtained. It turns out that even for very low values of k, one gets almost the same e±ciency as Tyler's M-estimator.

Original language	English
Place of Publication	Tilburg
Publisher	Econometrics
Number of pages	13
Volume	2010-41
Publication status	Published - 2010

Publication series

Name	CentER Discussion Paper
Volume	2010-41

Access to Document

2010-41

Fingerprint Dive into the research topics of 'The K-Step Spatial Sign Covariance Matrix'. Together they form a unique fingerprint.

Cite this

@techreport{b3c069e53f34475a9c1b154904836bf2,

title = "The K-Step Spatial Sign Covariance Matrix",

abstract = "The Sign Covariance Matrix is an orthogonal equivariant estimator of mul- tivariate scale. It is often used as an easy-to-compute and highly robust estimator. In this paper we propose a k-step version of the Sign Covariance Matrix, which improves its e±ciency while keeping the maximal breakdown point. If k tends to infinity, Tyler's M-estimator is obtained. It turns out that even for very low values of k, one gets almost the same e±ciency as Tyler's M-estimator.",

author = "C. Croux and C. Dehon and A. Yadine",

note = "Subsequently published in Advances in Data Analysis and Classification, 2010 Pagination: 13",

year = "2010",

language = "English",

volume = "2010-41",

series = "CentER Discussion Paper",

publisher = "Econometrics",

type = "WorkingPaper",

institution = "Econometrics",

}

TY - UNPB

T1 - The K-Step Spatial Sign Covariance Matrix

AU - Croux, C.

AU - Dehon, C.

AU - Yadine, A.

N1 - Subsequently published in Advances in Data Analysis and Classification, 2010 Pagination: 13

PY - 2010

Y1 - 2010

N2 - The Sign Covariance Matrix is an orthogonal equivariant estimator of mul- tivariate scale. It is often used as an easy-to-compute and highly robust estimator. In this paper we propose a k-step version of the Sign Covariance Matrix, which improves its e±ciency while keeping the maximal breakdown point. If k tends to infinity, Tyler's M-estimator is obtained. It turns out that even for very low values of k, one gets almost the same e±ciency as Tyler's M-estimator.

AB - The Sign Covariance Matrix is an orthogonal equivariant estimator of mul- tivariate scale. It is often used as an easy-to-compute and highly robust estimator. In this paper we propose a k-step version of the Sign Covariance Matrix, which improves its e±ciency while keeping the maximal breakdown point. If k tends to infinity, Tyler's M-estimator is obtained. It turns out that even for very low values of k, one gets almost the same e±ciency as Tyler's M-estimator.

M3 - Discussion paper

VL - 2010-41

T3 - CentER Discussion Paper

BT - The K-Step Spatial Sign Covariance Matrix

PB - Econometrics

CY - Tilburg

ER -