The random matrix regime of Maronna’s M-estimator with elliptically distributed samples

Abstract : This article demonstrates that the robust scatter matrix estimator C N ∈ C N ×N of a multivariate elliptical population x 1 ,. .. , x n ∈ C N originally proposed by Maronna in 1976, and defined as the solution (when existent) of an implicit equation, behaves similar to a well-known random matrix model in the limiting regime where the population N and sample n sizes grow at the same speed. We show precisely that C N ∈ C N ×N is defined for all n large with probability one and that, under some light hypotheses, ˆ C N − ˆ S N → 0 almost surely in spectral norm, wherê S N follows a classical random matrix model. As a corollary, the limiting eigenvalue distribution of C N is derived. This analysis finds applications in the fields of statistical inference and signal processing.
Type de document :
Article dans une revue
Journal of Multivariate Analysis, Elsevier, 2015, 139, pp.56-78. 〈10.1016/j.jmva.2015.02.020〉
Liste complète des métadonnées

Littérature citée [39 références]  Voir  Masquer  Télécharger

https://hal.archives-ouvertes.fr/hal-01242488
Contributeur : Matha Deghel <>
Soumis le : samedi 12 décembre 2015 - 17:55:09
Dernière modification le : vendredi 9 novembre 2018 - 13:38:02
Document(s) archivé(s) le : samedi 29 avril 2017 - 12:09:08

Fichier

robust_est_elliptic.pdf
Accord explicite pour ce dépôt

Identifiants

Citation

Romain Couillet, Frédéric Pascal, Jack W. Silverstein. The random matrix regime of Maronna’s M-estimator with elliptically distributed samples. Journal of Multivariate Analysis, Elsevier, 2015, 139, pp.56-78. 〈10.1016/j.jmva.2015.02.020〉. 〈hal-01242488〉

Partager

Métriques

Consultations de la notice

488

Téléchargements de fichiers

125