Robust location estimation with missing data

Autores
Sued, Raquel Mariela; Yohai, Victor Jaime
Año de publicación
2013
Idioma
inglés
Tipo de recurso
artículo
Estado
versión publicada
Descripción
In a missing data setting, we have a sample in which a vector of explanatory variables xi is observed for every subject i, while scalar responses yi are missing by happenstance on some individuals. In this work we propose robust estimators of the distribution of the responses assuming missing at random (MAR) data, under a semiparametric regression model. Our approach allows the consistent estimation of any weakly continuous functional of the response’s distribution. In particular, strongly consistent estimators of any continuous location functional, such as the median, L-functionals and M-functionals, are proposed. A robust fit for the regression model combined with the robust properties of the location functional gives rise to a robust recipe for estimating the location parameter. Robustness is quantified through the breakdown point of the proposed procedure. The asymptotic distribution of the location estimators is also derived. The proofs of the theorems are presented in Supplementary Material available online.
Avec les donnees manquantes, nous avons un ´ echantillon pour lequel les variables explicatives ´ xi sont observees pour chaque sujet ´ i, tandis que les variables reponses ´ yi sont manquantes au hasard pour quelques individus. Dans ce travail, nous proposons des estimateurs robustes pour la fonction de distribution des variables reponses en supposant que les donn ´ ees soient manquantes au hasard (MAR), sous un mod ´ ele ` de regression non param ´ etrique. Notre approche permet l’estimation coh ´ erente de n’importe quelle fonction- ´ nelle faiblement continue de la distribution des variables reponses. Plus particuli ´ erement, nous proposons des ` L- et M-fonctionnelles qui sont des estimateurs fortement coherents de n’importe quelle fonctionnelle con- ´ tinue du parametre de position (par exemple, la m ` ediane). Une m ´ ethode d’ajustement robuste du mod ´ ele de ` regression combin ´ ee aux propri ´ et´ es de robustesse des fonctionnelles de tendance centrale fournissent une ´ methode robuste pour l’estimation du param ´ etre de position. La robustesse de notre proc ` edure est mesur ´ ee´ a l’aide du point de rupture. Nous obtenons aussi la fonction de distribution asymptotique des estimateurs ` du parametre de position. Des suppl ` ements, contenant les d ´ emonstrations des th ´ eor ´ emes, sont disponibles ` en ligne.
Fil: Sued, Raquel Mariela. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales. Instituto de Cálculo; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina
Fil: Yohai, Victor Jaime. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales. Departamento de Matemática; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina
Materia
Missing at Random
M-Location Functional
Asymptotic Distribution
Breakdown Point
Nivel de accesibilidad
acceso abierto
Condiciones de uso
https://creativecommons.org/licenses/by-nc-sa/2.5/ar/
Repositorio
CONICET Digital (CONICET)
Institución
Consejo Nacional de Investigaciones Científicas y Técnicas
OAI Identificador
oai:ri.conicet.gov.ar:11336/15926

id CONICETDig_50c0ab7408c7850b61b4115c1bb8121e
oai_identifier_str oai:ri.conicet.gov.ar:11336/15926
network_acronym_str CONICETDig
repository_id_str 3498
network_name_str CONICET Digital (CONICET)
spelling Robust location estimation with missing dataSued, Raquel MarielaYohai, Victor JaimeMissing at RandomM-Location FunctionalAsymptotic DistributionBreakdown Pointhttps://purl.org/becyt/ford/1.1https://purl.org/becyt/ford/1In a missing data setting, we have a sample in which a vector of explanatory variables xi is observed for every subject i, while scalar responses yi are missing by happenstance on some individuals. In this work we propose robust estimators of the distribution of the responses assuming missing at random (MAR) data, under a semiparametric regression model. Our approach allows the consistent estimation of any weakly continuous functional of the response’s distribution. In particular, strongly consistent estimators of any continuous location functional, such as the median, L-functionals and M-functionals, are proposed. A robust fit for the regression model combined with the robust properties of the location functional gives rise to a robust recipe for estimating the location parameter. Robustness is quantified through the breakdown point of the proposed procedure. The asymptotic distribution of the location estimators is also derived. The proofs of the theorems are presented in Supplementary Material available online.Avec les donnees manquantes, nous avons un ´ echantillon pour lequel les variables explicatives ´ xi sont observees pour chaque sujet ´ i, tandis que les variables reponses ´ yi sont manquantes au hasard pour quelques individus. Dans ce travail, nous proposons des estimateurs robustes pour la fonction de distribution des variables reponses en supposant que les donn ´ ees soient manquantes au hasard (MAR), sous un mod ´ ele ` de regression non param ´ etrique. Notre approche permet l’estimation coh ´ erente de n’importe quelle fonction- ´ nelle faiblement continue de la distribution des variables reponses. Plus particuli ´ erement, nous proposons des ` L- et M-fonctionnelles qui sont des estimateurs fortement coherents de n’importe quelle fonctionnelle con- ´ tinue du parametre de position (par exemple, la m ` ediane). Une m ´ ethode d’ajustement robuste du mod ´ ele de ` regression combin ´ ee aux propri ´ et´ es de robustesse des fonctionnelles de tendance centrale fournissent une ´ methode robuste pour l’estimation du param ´ etre de position. La robustesse de notre proc ` edure est mesur ´ ee´ a l’aide du point de rupture. Nous obtenons aussi la fonction de distribution asymptotique des estimateurs ` du parametre de position. Des suppl ` ements, contenant les d ´ emonstrations des th ´ eor ´ emes, sont disponibles ` en ligne.Fil: Sued, Raquel Mariela. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales. Instituto de Cálculo; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas; ArgentinaFil: Yohai, Victor Jaime. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales. Departamento de Matemática; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas; ArgentinaStatistical Society of Canada2013-03info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionhttp://purl.org/coar/resource_type/c_6501info:ar-repo/semantics/articuloapplication/pdfapplication/pdfhttp://hdl.handle.net/11336/15926Sued, Raquel Mariela; Yohai, Victor Jaime; Robust location estimation with missing data; Statistical Society of Canada; Canadian Journal Of Statistics-revue Canadienne de Statistique; 41; 1; 3-2013; 111-1320319-5724enginfo:eu-repo/semantics/altIdentifier/doi/10.1002/cjs.11163info:eu-repo/semantics/altIdentifier/url/http://onlinelibrary.wiley.com/doi/10.1002/cjs.11163/abstractinfo:eu-repo/semantics/openAccesshttps://creativecommons.org/licenses/by-nc-sa/2.5/ar/reponame:CONICET Digital (CONICET)instname:Consejo Nacional de Investigaciones Científicas y Técnicas2025-09-03T09:58:15Zoai:ri.conicet.gov.ar:11336/15926instacron:CONICETInstitucionalhttp://ri.conicet.gov.ar/Organismo científico-tecnológicoNo correspondehttp://ri.conicet.gov.ar/oai/requestdasensio@conicet.gov.ar; lcarlino@conicet.gov.arArgentinaNo correspondeNo correspondeNo correspondeopendoar:34982025-09-03 09:58:16.024CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicasfalse
dc.title.none.fl_str_mv Robust location estimation with missing data
title Robust location estimation with missing data
spellingShingle Robust location estimation with missing data
Sued, Raquel Mariela
Missing at Random
M-Location Functional
Asymptotic Distribution
Breakdown Point
title_short Robust location estimation with missing data
title_full Robust location estimation with missing data
title_fullStr Robust location estimation with missing data
title_full_unstemmed Robust location estimation with missing data
title_sort Robust location estimation with missing data
dc.creator.none.fl_str_mv Sued, Raquel Mariela
Yohai, Victor Jaime
author Sued, Raquel Mariela
author_facet Sued, Raquel Mariela
Yohai, Victor Jaime
author_role author
author2 Yohai, Victor Jaime
author2_role author
dc.subject.none.fl_str_mv Missing at Random
M-Location Functional
Asymptotic Distribution
Breakdown Point
topic Missing at Random
M-Location Functional
Asymptotic Distribution
Breakdown Point
purl_subject.fl_str_mv https://purl.org/becyt/ford/1.1
https://purl.org/becyt/ford/1
dc.description.none.fl_txt_mv In a missing data setting, we have a sample in which a vector of explanatory variables xi is observed for every subject i, while scalar responses yi are missing by happenstance on some individuals. In this work we propose robust estimators of the distribution of the responses assuming missing at random (MAR) data, under a semiparametric regression model. Our approach allows the consistent estimation of any weakly continuous functional of the response’s distribution. In particular, strongly consistent estimators of any continuous location functional, such as the median, L-functionals and M-functionals, are proposed. A robust fit for the regression model combined with the robust properties of the location functional gives rise to a robust recipe for estimating the location parameter. Robustness is quantified through the breakdown point of the proposed procedure. The asymptotic distribution of the location estimators is also derived. The proofs of the theorems are presented in Supplementary Material available online.
Avec les donnees manquantes, nous avons un ´ echantillon pour lequel les variables explicatives ´ xi sont observees pour chaque sujet ´ i, tandis que les variables reponses ´ yi sont manquantes au hasard pour quelques individus. Dans ce travail, nous proposons des estimateurs robustes pour la fonction de distribution des variables reponses en supposant que les donn ´ ees soient manquantes au hasard (MAR), sous un mod ´ ele ` de regression non param ´ etrique. Notre approche permet l’estimation coh ´ erente de n’importe quelle fonction- ´ nelle faiblement continue de la distribution des variables reponses. Plus particuli ´ erement, nous proposons des ` L- et M-fonctionnelles qui sont des estimateurs fortement coherents de n’importe quelle fonctionnelle con- ´ tinue du parametre de position (par exemple, la m ` ediane). Une m ´ ethode d’ajustement robuste du mod ´ ele de ` regression combin ´ ee aux propri ´ et´ es de robustesse des fonctionnelles de tendance centrale fournissent une ´ methode robuste pour l’estimation du param ´ etre de position. La robustesse de notre proc ` edure est mesur ´ ee´ a l’aide du point de rupture. Nous obtenons aussi la fonction de distribution asymptotique des estimateurs ` du parametre de position. Des suppl ` ements, contenant les d ´ emonstrations des th ´ eor ´ emes, sont disponibles ` en ligne.
Fil: Sued, Raquel Mariela. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales. Instituto de Cálculo; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina
Fil: Yohai, Victor Jaime. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales. Departamento de Matemática; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina
description In a missing data setting, we have a sample in which a vector of explanatory variables xi is observed for every subject i, while scalar responses yi are missing by happenstance on some individuals. In this work we propose robust estimators of the distribution of the responses assuming missing at random (MAR) data, under a semiparametric regression model. Our approach allows the consistent estimation of any weakly continuous functional of the response’s distribution. In particular, strongly consistent estimators of any continuous location functional, such as the median, L-functionals and M-functionals, are proposed. A robust fit for the regression model combined with the robust properties of the location functional gives rise to a robust recipe for estimating the location parameter. Robustness is quantified through the breakdown point of the proposed procedure. The asymptotic distribution of the location estimators is also derived. The proofs of the theorems are presented in Supplementary Material available online.
publishDate 2013
dc.date.none.fl_str_mv 2013-03
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
http://purl.org/coar/resource_type/c_6501
info:ar-repo/semantics/articulo
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv http://hdl.handle.net/11336/15926
Sued, Raquel Mariela; Yohai, Victor Jaime; Robust location estimation with missing data; Statistical Society of Canada; Canadian Journal Of Statistics-revue Canadienne de Statistique; 41; 1; 3-2013; 111-132
0319-5724
url http://hdl.handle.net/11336/15926
identifier_str_mv Sued, Raquel Mariela; Yohai, Victor Jaime; Robust location estimation with missing data; Statistical Society of Canada; Canadian Journal Of Statistics-revue Canadienne de Statistique; 41; 1; 3-2013; 111-132
0319-5724
dc.language.none.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv info:eu-repo/semantics/altIdentifier/doi/10.1002/cjs.11163
info:eu-repo/semantics/altIdentifier/url/http://onlinelibrary.wiley.com/doi/10.1002/cjs.11163/abstract
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
https://creativecommons.org/licenses/by-nc-sa/2.5/ar/
eu_rights_str_mv openAccess
rights_invalid_str_mv https://creativecommons.org/licenses/by-nc-sa/2.5/ar/
dc.format.none.fl_str_mv application/pdf
application/pdf
dc.publisher.none.fl_str_mv Statistical Society of Canada
publisher.none.fl_str_mv Statistical Society of Canada
dc.source.none.fl_str_mv reponame:CONICET Digital (CONICET)
instname:Consejo Nacional de Investigaciones Científicas y Técnicas
reponame_str CONICET Digital (CONICET)
collection CONICET Digital (CONICET)
instname_str Consejo Nacional de Investigaciones Científicas y Técnicas
repository.name.fl_str_mv CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicas
repository.mail.fl_str_mv dasensio@conicet.gov.ar; lcarlino@conicet.gov.ar
_version_ 1842269511238025216
score 13.13397