Robust M-estimator of scatter for large elliptical samples

Abstract : It is shown that Maronna's robust M-estimator of scatter for elliptical samples behaves similar to an analytically tractable random matrix model in the limiting regime where both the population N and sample n sizes grow to infinity at the same speed. This result allows us to understand the structure of such estimators and in particular to derive their limiting eigenvalue distributions. This analysis is a first step towards an improved usage of robust estimation methods when the number of independent observations is not too large compared to the size of the population.
Type de document :
Communication dans un congrès
IEEE SSP'14, Jun 2014, Gold Coast, Australia. Proceedings of the 2014 IEEE Workshop on Statistical Signal Processing, pp.1-4, 〈10.1109/SSP.2014.6884560〉
Liste complète des métadonnées

https://hal-supelec.archives-ouvertes.fr/hal-01092916
Contributeur : Catherine Magnet <>
Soumis le : mardi 9 décembre 2014 - 16:49:37
Dernière modification le : mercredi 4 avril 2018 - 10:32:03

Identifiants

Collections

Citation

Romain Couillet, F. Pascal. Robust M-estimator of scatter for large elliptical samples. IEEE SSP'14, Jun 2014, Gold Coast, Australia. Proceedings of the 2014 IEEE Workshop on Statistical Signal Processing, pp.1-4, 〈10.1109/SSP.2014.6884560〉. 〈hal-01092916〉

Partager

Métriques

Consultations de la notice

101