Influence function and efficiency of the minimum covariance determinant scatter matrix estimator

Croux, C.; Haesbroeck, Gentiane

doi:10.1006/jmva.1999.1839

Request a copy

Article (Scientific journals)

Influence function and efficiency of the minimum covariance determinant scatter matrix estimator

Croux, C.; Haesbroeck, Gentiane

1999 • In Journal of Multivariate Analysis, 71 (2), p. 161-190

Peer Reviewed verified by ORBi

Permalink
https://hdl.handle.net/2268/28466

DOI
10.1006/jmva.1999.1839

Files (1)Send to Details Statistics Bibliography Similar publications

Files

Full Text

text.pdf

Author preprint (640.69 kB)

Request a copy

All documents in ORBi are protected by a user license.

Send to

RIS BibTex APA Chicago Permalink X Linkedin

Details

Keywords :

influence function; minimum covariance determinant estimator; robust estimation; scatter matrix

Abstract :

[en] The minimum covariance determinant (MCD) scatter estimator is a highly robust estimator for the dispersion matrix of a multivariate, elliptically symmetric distribution. It is relatively fast to compute and intuitively appealing. In this note we derive its influence function and compute the asymptotic variances of its elements. A comparison with the one step reweighted MCD and with S-estimators is made. Also finite-sample results are reported. (C) 1999 Academic Press AMS 1991 subject classifications: 62F35, 62G35.

Disciplines :

Mathematics

Author, co-author :

Croux, C.

Haesbroeck, Gentiane ; Université de Liège - ULiège > Département de mathématique > Statistique (aspects théoriques)

Language :

English

Title :

Influence function and efficiency of the minimum covariance determinant scatter matrix estimator

Publication date :

1999

Journal title :

Journal of Multivariate Analysis

ISSN :

0047-259X

eISSN :

1095-7243

Publisher :

Academic Press

Volume :

Issue :

Pages :

161-190

Peer reviewed :

Peer Reviewed verified by ORBi

Available on ORBi :

since 18 November 2009

Statistics

Number of views

113 (9 by ULiège)

Number of downloads

4 (1 by ULiège)

More statistics

Scopus citations^®

191

Scopus citations^®
without self-citations

164

OpenCitations

175

OpenAlex citations

256

Bibliography

Bickel P. J., Lehmann E. L. Descriptive statistics for nonparametric models III, Dispersion. Ann. Statist. 4:1976;1139-1159.
Butler R. W. Nonparametric interval and point prediction using data trimmed by a Grubbs type outlier rule. Ann. Statist. 10:1982;197-204.
Butler R. W., Davies P. L., Jhun M. Asymptotics for the minimum covariance determinant estimator. Ann. Statist. 21:1993;1385-1400.
Croux C., Rousseeuw P. J. A class of high-breakdown scale estimators based on subranges. Comm. Statist. Theory Methods. 21:1992;1935-1951.
Croux C., Haesbroeck G. Technical Report. 1999.
Davies P. L. Asymptotic behavior of S-estimators of multivariate location parameters and dispersion matrices. Ann. Statist. 15:1987;1269-1292.
Davies P. L. The asymptotics of Rousseeuw's minimum volume ellipsoid. Ann. Statist. 20:1992a;1828-1843.
Davies P. L. An efficient Fréchet Differentiable high breakdown multivariate location and dispersion estimator. J. Multivariate Anal. 40:1992b;311-327.
Grübel R. A minimal characterization of the covariance matrix. Metrika. 35:1988;49-52.
Hampel F. R., Ronchetti E. M., Rousseeuw P. J., Stahel W. A. Robust Statistics: The Approach Based on Influence Functions. 1996;Wiley, New York.
Hawkins D. M. The feasible solution algorithm for the minimum covariance determinant estimator in multivariate data. Comput. Statist. Data Anal. 17:1994;197-210.
He X., Wang G. Cross-checking using the minimum volume ellipsoid estimator. Statistica Sinica. 6:1996;367-374.
Hössjer O., Croux C. Generalizing univariate signed rank statistics for testing and estimating a multivariate location parameter. Nonparametric Statist. 4:1995;293-308.
Lopuhaä H. P. On the relation between S-estimators and M-estimators of multivariate location and covariance. Ann. Statist. 17:1989;1662-1683.
Lopuhaä H. P. Multivariate τ-estimators for location and scatter. Canad. J. Statist. 19:1991;307-321.
Lopuhaä H. P. Highly efficient estimators of multivariate location with high breakdown point. Ann. Statist. 19:1992;229-248.
H. P. Lopuhaä, Asymptotics of reweighted estimators of multivariate location and scatter, preprint, TU Delft, 1997.
Lopuhaä H. P., Rousseeuw P. J. Breakdown properties of affine equivariant estimators of multivariate location and covariance matrices. Ann. Statist. 19:1991;229-248.
Maronna R. A., Yohai. Robust estimation of multivariate location and scatter. Kotz S., Read C., Banks D. Encyclopedia of Statistical Sciences Update. 1998;589-596 Wiley, New York.
Rocke D. M. Robustness properties of S-estimators of multivariate location and shape in high dimensions. Ann. Statist. 24:1996;1327-1345.
Rousseeuw P. J. Multivariate estimation with high breakdown point. Grossmann W., Pflug G., Vincze I., Wertz W. Mathematical Statistics and Applications. 1985;283-297 Reidel, Dordrecht.
Rousseeuw P. J., Leroy A. M. Robust Regression and Outlier Detection. 1987;Wiley, New York.
Rousseeuw P. J., Croux C. The bias of k-step M-estimators. Statist. Probab. Lett. 20:1994;411-420.
P. J. Rousseeuw, and, K. Van Driessen, A fast algorithm for the minimum covariance determinant estimator, Technometrics, to appear.
Ruppert D. Computing S-estimators for regression and multivariate location/dispersion. J. Comput. Graph. Statist. 1:1992;253-270.
Yohai V. J., Maronna R. A. The maximum bias of robust covariances. Comm. Statist. A. 19:1990;3924-3933.