Robust Mean and Covariance Matrix Estimation Under Heterogeneous Mixed-Effects Model - Archive ouverte HAL Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2021

Robust Mean and Covariance Matrix Estimation Under Heterogeneous Mixed-Effects Model

Résumé

In this paper, robust mean and covariance matrix estimation are considered in the context of mixed-effects models. Such models are widely used to analyze repeated measures data which arise in several signal processing applications that need to incorporate a same global individuals behavior with a possible individual variations. In this context, most algorithms are based on Gaussian assumption of the observations. Nevertheless, in certain situations in which there exist outliers within the data set, such assumption is not valid and leads to a dramatic performance loss. To overcome this drawback, we design an expectation-conditional maximization either algorithm in which the heterogeneous component is considered as part of the complete data. Then, the proposed algorithm is cast into a parallel scheme, w.r.t. the individuals, in order to alleviate the computational cost and a possible central processor overload. Finally, the proposed algorithm is extended to deal with missing data which refers to the situation where part of the individual responses are unobserved. Numerical simulations are performed in order to assess the performance of the proposed algorithm in regard to robust regression estimators, probabilistic principal component analysis and its recent robust version.
Fichier principal
Vignette du fichier
ELKORSO_HAL.pdf (364.54 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03156771 , version 1 (02-03-2021)

Identifiants

  • HAL Id : hal-03156771 , version 1

Citer

Alexandre Hippert-Ferrer, M. N. El Korso, Arnaud Breloy, Guillaume Ginolhac. Robust Mean and Covariance Matrix Estimation Under Heterogeneous Mixed-Effects Model. 2021. ⟨hal-03156771⟩
56 Consultations
204 Téléchargements

Partager

Gmail Facebook X LinkedIn More