Estimates of MM type for the multivariate linear model

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Kudraszow, Nadia L., Maronna, Ricardo A.
Natura: Preprint
Pubblicazione: 2010
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908684621185024
author Kudraszow, Nadia L.
Maronna, Ricardo A.
author_facet Kudraszow, Nadia L.
Maronna, Ricardo A.
contents We propose a class of robust estimates for multivariate linear models. Based on the approach of MM estimation (Yohai 1987), we estimate the regression coefficients and the covariance matrix of the errors simultaneously. These estimates have both high breakdown point and high asymptotic efficiency under Gaussian errors. We prove consistency and asymptotic normality assuming errors with an elliptical distribution. We describe an iterative algorithm for the numerical calculation of these estimates. The advantages of the proposed estimates over their competitors are demonstrated through both simulated and real data.
format Preprint
id arxiv_https___arxiv_org_abs_1004_4883
institution arXiv
publishDate 2010
record_format arxiv
spellingShingle Estimates of MM type for the multivariate linear model
Kudraszow, Nadia L.
Maronna, Ricardo A.
Statistics Theory
We propose a class of robust estimates for multivariate linear models. Based on the approach of MM estimation (Yohai 1987), we estimate the regression coefficients and the covariance matrix of the errors simultaneously. These estimates have both high breakdown point and high asymptotic efficiency under Gaussian errors. We prove consistency and asymptotic normality assuming errors with an elliptical distribution. We describe an iterative algorithm for the numerical calculation of these estimates. The advantages of the proposed estimates over their competitors are demonstrated through both simulated and real data.
title Estimates of MM type for the multivariate linear model
topic Statistics Theory
url https://arxiv.org/abs/1004.4883