Robust discrimination under a hierarchy on the scatter matrices
Under normality, Flury and Schmid [Quadratic discriminant functions with constraints on the covariances matrices: some asymptotic results, J. Multivariate Anal. 40 (1992) 244-261] investigated the asymptotic properties of the quadratic discrimination procedure under hierarchical models for the scatt...
Guardado en:
Autores principales: | , , , |
---|---|
Formato: | Artículo publishedVersion |
Lenguaje: | Inglés |
Publicado: |
2008
|
Materias: | |
Acceso en línea: | http://hdl.handle.net/20.500.12110/paper_0047259X_v99_n6_p1332_Bianco |
Aporte de: |
id |
paperaa:paper_0047259X_v99_n6_p1332_Bianco |
---|---|
record_format |
dspace |
spelling |
paperaa:paper_0047259X_v99_n6_p1332_Bianco2023-06-12T16:45:41Z Robust discrimination under a hierarchy on the scatter matrices J. Multivariate Anal. 2008;99(6):1332-1357 Bianco, A. Boente, G. Pires, A.M. Rodrigues, I.M. Common principal components Outliers Partial influence functions Plug-in methods Proportional scatter matrices Quadratic discrimination Robust estimation Under normality, Flury and Schmid [Quadratic discriminant functions with constraints on the covariances matrices: some asymptotic results, J. Multivariate Anal. 40 (1992) 244-261] investigated the asymptotic properties of the quadratic discrimination procedure under hierarchical models for the scatter matrices, that is: (i) arbitrary scatter matrices, (ii) common principal components, (iii) proportional scatter matrices and (iv) identical matrices. In this paper, we study the properties of robust quadratic discrimination rules based on robust estimates of the involved parameters. Our analysis is based on the partial influence functions of the functionals related to these parameters and allows to derive the asymptotic variances of the estimated coefficients under models (i)-(iv). From them, we conclude that the asymptotic variances verify the same order relations as those obtained by Flury and Schmid [Quadratic discriminant functions with constraints on the covariances matrices: some asymptotic results, J. Multivariate Anal. 40 (1992) 244-261] for the classical estimators. We also perform a Monte Carlo study for different sample sizes and different hierarchies which shows the advantage of using robust procedures over classical ones, when anomalous data are present. It also confirms that better rates of misclassification can be achieved if a more parsimonious model among all the correct ones is used instead of the standard quadratic discrimination. © 2007 Elsevier Inc. All rights reserved. Fil:Bianco, A. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales; Argentina. Fil:Boente, G. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales; Argentina. 2008 info:eu-repo/semantics/article info:ar-repo/semantics/artículo info:eu-repo/semantics/publishedVersion application/pdf eng info:eu-repo/semantics/openAccess http://creativecommons.org/licenses/by/2.5/ar http://hdl.handle.net/20.500.12110/paper_0047259X_v99_n6_p1332_Bianco |
institution |
Universidad de Buenos Aires |
institution_str |
I-28 |
repository_str |
R-134 |
collection |
Biblioteca Digital - Facultad de Ciencias Exactas y Naturales (UBA) |
language |
Inglés |
orig_language_str_mv |
eng |
topic |
Common principal components Outliers Partial influence functions Plug-in methods Proportional scatter matrices Quadratic discrimination Robust estimation |
spellingShingle |
Common principal components Outliers Partial influence functions Plug-in methods Proportional scatter matrices Quadratic discrimination Robust estimation Bianco, A. Boente, G. Pires, A.M. Rodrigues, I.M. Robust discrimination under a hierarchy on the scatter matrices |
topic_facet |
Common principal components Outliers Partial influence functions Plug-in methods Proportional scatter matrices Quadratic discrimination Robust estimation |
description |
Under normality, Flury and Schmid [Quadratic discriminant functions with constraints on the covariances matrices: some asymptotic results, J. Multivariate Anal. 40 (1992) 244-261] investigated the asymptotic properties of the quadratic discrimination procedure under hierarchical models for the scatter matrices, that is: (i) arbitrary scatter matrices, (ii) common principal components, (iii) proportional scatter matrices and (iv) identical matrices. In this paper, we study the properties of robust quadratic discrimination rules based on robust estimates of the involved parameters. Our analysis is based on the partial influence functions of the functionals related to these parameters and allows to derive the asymptotic variances of the estimated coefficients under models (i)-(iv). From them, we conclude that the asymptotic variances verify the same order relations as those obtained by Flury and Schmid [Quadratic discriminant functions with constraints on the covariances matrices: some asymptotic results, J. Multivariate Anal. 40 (1992) 244-261] for the classical estimators. We also perform a Monte Carlo study for different sample sizes and different hierarchies which shows the advantage of using robust procedures over classical ones, when anomalous data are present. It also confirms that better rates of misclassification can be achieved if a more parsimonious model among all the correct ones is used instead of the standard quadratic discrimination. © 2007 Elsevier Inc. All rights reserved. |
format |
Artículo Artículo publishedVersion |
author |
Bianco, A. Boente, G. Pires, A.M. Rodrigues, I.M. |
author_facet |
Bianco, A. Boente, G. Pires, A.M. Rodrigues, I.M. |
author_sort |
Bianco, A. |
title |
Robust discrimination under a hierarchy on the scatter matrices |
title_short |
Robust discrimination under a hierarchy on the scatter matrices |
title_full |
Robust discrimination under a hierarchy on the scatter matrices |
title_fullStr |
Robust discrimination under a hierarchy on the scatter matrices |
title_full_unstemmed |
Robust discrimination under a hierarchy on the scatter matrices |
title_sort |
robust discrimination under a hierarchy on the scatter matrices |
publishDate |
2008 |
url |
http://hdl.handle.net/20.500.12110/paper_0047259X_v99_n6_p1332_Bianco |
work_keys_str_mv |
AT biancoa robustdiscriminationunderahierarchyonthescattermatrices AT boenteg robustdiscriminationunderahierarchyonthescattermatrices AT piresam robustdiscriminationunderahierarchyonthescattermatrices AT rodriguesim robustdiscriminationunderahierarchyonthescattermatrices |
_version_ |
1769810328036573184 |