The choice of the initial estimate for computing MM-estimates

We show, using a Monte Carlo study, that MM-estimates with projection estimates as starting point of an iterative weighted least squares algorithm, behave more robustly than MM-estimates starting at an S-estimate and similar Gaussian efficiency. Moreover the former have a robustness behavior close t...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Svarc, M., Yohai, V.J., et al.; Fundacao para a Ciencia e a Tecnologia (FCT); Instituto Nacional de Estatistica; PORTO Camara Municipal; PSE; Universidade do Porto - Faculdade de Engenharia (FEUP)
Formato: CONF
Materias:
P-estimates
Robust regression
S-estimates
Gaussians
Initial estimate
Iterative-weighted
Robust regressions
Statistical inference
Iterative methods
Acceso en línea:http://hdl.handle.net/20.500.12110/paper_97837908_v_n_p503_Svarc
Aporte de:
Biblioteca Digital - Facultad de Ciencias Exactas y Naturales (UBA) de Universidad de Buenos Aires
id todo:paper_97837908_v_n_p503_Svarc
record_format dspace
spelling todo:paper_97837908_v_n_p503_Svarc2023-10-03T16:45:15Z The choice of the initial estimate for computing MM-estimates Svarc, M. Yohai, V.J. et al.; Fundacao para a Ciencia e a Tecnologia (FCT); Instituto Nacional de Estatistica; PORTO Camara Municipal; PSE; Universidade do Porto - Faculdade de Engenharia (FEUP) P-estimates Robust regression S-estimates Gaussians Initial estimate Iterative-weighted P-estimates Robust regressions S-estimates Statistical inference Iterative methods We show, using a Monte Carlo study, that MM-estimates with projection estimates as starting point of an iterative weighted least squares algorithm, behave more robustly than MM-estimates starting at an S-estimate and similar Gaussian efficiency. Moreover the former have a robustness behavior close to the P-estimates with an additional advantage: they are asymptotically normal making statistical inference possible. Fil:Svarc, M. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales; Argentina. CONF info:eu-repo/semantics/openAccess http://creativecommons.org/licenses/by/2.5/ar http://hdl.handle.net/20.500.12110/paper_97837908_v_n_p503_Svarc
institution Universidad de Buenos Aires
institution_str I-28
repository_str R-134
collection Biblioteca Digital - Facultad de Ciencias Exactas y Naturales (UBA)
topic P-estimates
Robust regression
S-estimates
Gaussians
Initial estimate
Iterative-weighted
P-estimates
Robust regressions
S-estimates
Statistical inference
Iterative methods
spellingShingle P-estimates
Robust regression
S-estimates
Gaussians
Initial estimate
Iterative-weighted
P-estimates
Robust regressions
S-estimates
Statistical inference
Iterative methods
Svarc, M.
Yohai, V.J.
et al.; Fundacao para a Ciencia e a Tecnologia (FCT); Instituto Nacional de Estatistica; PORTO Camara Municipal; PSE; Universidade do Porto - Faculdade de Engenharia (FEUP)
The choice of the initial estimate for computing MM-estimates
topic_facet P-estimates
Robust regression
S-estimates
Gaussians
Initial estimate
Iterative-weighted
P-estimates
Robust regressions
S-estimates
Statistical inference
Iterative methods
description We show, using a Monte Carlo study, that MM-estimates with projection estimates as starting point of an iterative weighted least squares algorithm, behave more robustly than MM-estimates starting at an S-estimate and similar Gaussian efficiency. Moreover the former have a robustness behavior close to the P-estimates with an additional advantage: they are asymptotically normal making statistical inference possible.
format CONF
author Svarc, M.
Yohai, V.J.
et al.; Fundacao para a Ciencia e a Tecnologia (FCT); Instituto Nacional de Estatistica; PORTO Camara Municipal; PSE; Universidade do Porto - Faculdade de Engenharia (FEUP)
author_facet Svarc, M.
Yohai, V.J.
et al.; Fundacao para a Ciencia e a Tecnologia (FCT); Instituto Nacional de Estatistica; PORTO Camara Municipal; PSE; Universidade do Porto - Faculdade de Engenharia (FEUP)
author_sort Svarc, M.
title The choice of the initial estimate for computing MM-estimates
title_short The choice of the initial estimate for computing MM-estimates
title_full The choice of the initial estimate for computing MM-estimates
title_fullStr The choice of the initial estimate for computing MM-estimates
title_full_unstemmed The choice of the initial estimate for computing MM-estimates
title_sort choice of the initial estimate for computing mm-estimates
url http://hdl.handle.net/20.500.12110/paper_97837908_v_n_p503_Svarc
work_keys_str_mv AT svarcm thechoiceoftheinitialestimateforcomputingmmestimates
AT yohaivj thechoiceoftheinitialestimateforcomputingmmestimates
AT etalfundacaoparaacienciaeatecnologiafctinstitutonacionaldeestatisticaportocamaramunicipalpseuniversidadedoportofaculdadedeengenhariafeup thechoiceoftheinitialestimateforcomputingmmestimates
AT svarcm choiceoftheinitialestimateforcomputingmmestimates
AT yohaivj choiceoftheinitialestimateforcomputingmmestimates
AT etalfundacaoparaacienciaeatecnologiafctinstitutonacionaldeestatisticaportocamaramunicipalpseuniversidadedoportofaculdadedeengenhariafeup choiceoftheinitialestimateforcomputingmmestimates
_version_ 1807321124630953984

Ejemplares similares