Robust sieve estimators for functional canonical correlation analysis

In this paper, we propose robust estimators for the first canonical correlation and directions of random elements on Hilbert separable spaces by combining sieves and robust association measures, leading to Fisher-consistent estimators for appropriate choices of the association measure. Under regular...

Descripción completa

Guardado en:
Detalles Bibliográficos
Publicado: 2019
Materias:
Canonical correlation
Fisher-consistency
Functional data
Robust estimation
Sieves
Acceso en línea:https://bibliotecadigital.exactas.uba.ar/collection/paper/document/paper_0047259X_v170_n_p46_Alvarez
http://hdl.handle.net/20.500.12110/paper_0047259X_v170_n_p46_Alvarez
Aporte de:
Biblioteca Digital - Facultad de Ciencias Exactas y Naturales (UBA) de Universidad de Buenos Aires
id paper:paper_0047259X_v170_n_p46_Alvarez
record_format dspace
spelling paper:paper_0047259X_v170_n_p46_Alvarez2023-06-08T15:05:36Z Robust sieve estimators for functional canonical correlation analysis Canonical correlation Fisher-consistency Functional data Robust estimation Sieves In this paper, we propose robust estimators for the first canonical correlation and directions of random elements on Hilbert separable spaces by combining sieves and robust association measures, leading to Fisher-consistent estimators for appropriate choices of the association measure. Under regularity conditions, the resulting estimators are consistent. The robust procedure allows us to construct detection rules to identify possible influential observations. The finite sample performance is illustrated through a simulation study in which contaminated data is included. The benefits of considering robust estimators are also illustrated on a real data set where the detection methods reveal the presence of influential observations for the first canonical directions that would be missed otherwise. © 2018 Elsevier Inc. 2019 https://bibliotecadigital.exactas.uba.ar/collection/paper/document/paper_0047259X_v170_n_p46_Alvarez http://hdl.handle.net/20.500.12110/paper_0047259X_v170_n_p46_Alvarez
institution Universidad de Buenos Aires
institution_str I-28
repository_str R-134
collection Biblioteca Digital - Facultad de Ciencias Exactas y Naturales (UBA)
topic Canonical correlation
Fisher-consistency
Functional data
Robust estimation
Sieves
spellingShingle Canonical correlation
Fisher-consistency
Functional data
Robust estimation
Sieves
Robust sieve estimators for functional canonical correlation analysis
topic_facet Canonical correlation
Fisher-consistency
Functional data
Robust estimation
Sieves
description In this paper, we propose robust estimators for the first canonical correlation and directions of random elements on Hilbert separable spaces by combining sieves and robust association measures, leading to Fisher-consistent estimators for appropriate choices of the association measure. Under regularity conditions, the resulting estimators are consistent. The robust procedure allows us to construct detection rules to identify possible influential observations. The finite sample performance is illustrated through a simulation study in which contaminated data is included. The benefits of considering robust estimators are also illustrated on a real data set where the detection methods reveal the presence of influential observations for the first canonical directions that would be missed otherwise. © 2018 Elsevier Inc.
title Robust sieve estimators for functional canonical correlation analysis
title_short Robust sieve estimators for functional canonical correlation analysis
title_full Robust sieve estimators for functional canonical correlation analysis
title_fullStr Robust sieve estimators for functional canonical correlation analysis
title_full_unstemmed Robust sieve estimators for functional canonical correlation analysis
title_sort robust sieve estimators for functional canonical correlation analysis
publishDate 2019
url https://bibliotecadigital.exactas.uba.ar/collection/paper/document/paper_0047259X_v170_n_p46_Alvarez
http://hdl.handle.net/20.500.12110/paper_0047259X_v170_n_p46_Alvarez
_version_ 1768542074530955264

Ejemplares similares