The Maximum Bias of Robust Covariances : Notas de Matemática, 46

This paper deals with the maximum asymptotic bias of tiro classes of robust estimates of the dispersion matrix V of a p-dimensional random vector z, under a contamination model of the form P = (1—ε)Po+δ(x0), where P is the distribution of z, Po is a spherical distribution, and δ(x0) is a point mass...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Maronna, Ricardo Antonio, Yohai, Víctor Jaime
Formato: Publicacion seriada
Lenguaje:Inglés
Publicado: 1987
Materias:
Acceso en línea:http://sedici.unlp.edu.ar/handle/10915/168837
Aporte de:
id I19-R120-10915-168837
record_format dspace
spelling I19-R120-10915-1688372024-08-22T04:08:07Z http://sedici.unlp.edu.ar/handle/10915/168837 The Maximum Bias of Robust Covariances : Notas de Matemática, 46 Maronna, Ricardo Antonio Yohai, Víctor Jaime 1987 2024-08-21T16:48:23Z en Matemática Robust covariance maximum bias M-estimators high breakdown point estimators This paper deals with the maximum asymptotic bias of tiro classes of robust estimates of the dispersion matrix V of a p-dimensional random vector z, under a contamination model of the form P = (1—ε)Po+δ(x0), where P is the distribution of z, Po is a spherical distribution, and δ(x0) is a point mass at z0. Estimators VQ,α of the first class minimise the α quantile of x´V-1z among all symmetric positive-definite matrices V for some α ϵ (0,1). The "maximum volume ellipsoid" estimator proposed by Rouseauw belongs to this class with α = 0.5. These estimators have breakdown point min(α, 1 - α) for all p. The second class of estimators constat of the M-estimaton, from which the seemingly most robust member was choses; namely the Tyler estimate defined as the solution VT of Ez´VT-1z/z´z = VT. This estimator has breakdown point 1/p. The numerical results show that except for ε very close to 1/p, VT has in general a smaller máximum bias than VQ,α; and that the maximum bias of the latter may be extremely large even for a much smaller than its breakdown point. Material digitalizado en SEDICI gracias a la colaboración de la Biblioteca del Departamento de Matemática de la Facultad de Ciencias Exactas (UNLP). Facultad de Ciencias Exactas Publicacion seriada Publicacion seriada http://creativecommons.org/licenses/by-nc-sa/4.0/ Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0) application/pdf
institution Universidad Nacional de La Plata
institution_str I-19
repository_str R-120
collection SEDICI (UNLP)
language Inglés
topic Matemática
Robust covariance
maximum bias
M-estimators
high breakdown point estimators
spellingShingle Matemática
Robust covariance
maximum bias
M-estimators
high breakdown point estimators
Maronna, Ricardo Antonio
Yohai, Víctor Jaime
The Maximum Bias of Robust Covariances : Notas de Matemática, 46
topic_facet Matemática
Robust covariance
maximum bias
M-estimators
high breakdown point estimators
description This paper deals with the maximum asymptotic bias of tiro classes of robust estimates of the dispersion matrix V of a p-dimensional random vector z, under a contamination model of the form P = (1—ε)Po+δ(x0), where P is the distribution of z, Po is a spherical distribution, and δ(x0) is a point mass at z0. Estimators VQ,α of the first class minimise the α quantile of x´V-1z among all symmetric positive-definite matrices V for some α ϵ (0,1). The "maximum volume ellipsoid" estimator proposed by Rouseauw belongs to this class with α = 0.5. These estimators have breakdown point min(α, 1 - α) for all p. The second class of estimators constat of the M-estimaton, from which the seemingly most robust member was choses; namely the Tyler estimate defined as the solution VT of Ez´VT-1z/z´z = VT. This estimator has breakdown point 1/p. The numerical results show that except for ε very close to 1/p, VT has in general a smaller máximum bias than VQ,α; and that the maximum bias of the latter may be extremely large even for a much smaller than its breakdown point.
format Publicacion seriada
Publicacion seriada
author Maronna, Ricardo Antonio
Yohai, Víctor Jaime
author_facet Maronna, Ricardo Antonio
Yohai, Víctor Jaime
author_sort Maronna, Ricardo Antonio
title The Maximum Bias of Robust Covariances : Notas de Matemática, 46
title_short The Maximum Bias of Robust Covariances : Notas de Matemática, 46
title_full The Maximum Bias of Robust Covariances : Notas de Matemática, 46
title_fullStr The Maximum Bias of Robust Covariances : Notas de Matemática, 46
title_full_unstemmed The Maximum Bias of Robust Covariances : Notas de Matemática, 46
title_sort maximum bias of robust covariances : notas de matemática, 46
publishDate 1987
url http://sedici.unlp.edu.ar/handle/10915/168837
work_keys_str_mv AT maronnaricardoantonio themaximumbiasofrobustcovariancesnotasdematematica46
AT yohaivictorjaime themaximumbiasofrobustcovariancesnotasdematematica46
AT maronnaricardoantonio maximumbiasofrobustcovariancesnotasdematematica46
AT yohaivictorjaime maximumbiasofrobustcovariancesnotasdematematica46
_version_ 1809234820998365184