• Citer

Influence Function and Efficiency of the Minimum Covariance Determinant Scatter Matrix Estimator

par Croux, Christophe ;Haesbroeck, Gentiane
Référence Journal of Multivariate Analysis, 71, 2, page (161-190)
Publication Publié, 1999-11

Article révisé par les pairs

• Détails
• Contenu

Résumé :

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. © 1999 Academic Press.