Publicação

A robust sparse linear approach for contaminated data

Ver documento

Detalhes bibliográficos
Resumo:A challenging problem in a linear regression model is to select a parsimonious model which is robust to the presence of contamination in the data. In this paper, we present a sparse linear approach which detects outliers by using a highly robust regression method. The model with optimal predictive ability as measured by the median absolute deviation of the prediction errors on JackKnife subsets is used to detect outliers. The performance of the proposed method is evaluated on a simulation study with a different type of outliers and high leverage points and also on a real data set.
Autores principais:Shahriari, S
Outros Autores:Faria, S; Manuela Gonçalves, A
Assunto:JackKnife Outlier detection Robust variable selection Sparsity
Ano:2019
País:Portugal
Tipo de documento:artigo
Tipo de acesso:acesso restrito
Instituição associada:Universidade do Porto
Idioma:inglês
Origem:Repositório Aberto da Universidade do Porto
_version_ 1867768468109000704
author Shahriari, S
author2 Faria, S
Manuela Gonçalves, A
author2_role author
author
author_facet Shahriari, S
Faria, S
Manuela Gonçalves, A
author_role author
country_str PT
creators_json_txt [{\"Person.name\":\"Shahriari, S\"},{\"Person.name\":\"Faria, S\"},{\"Person.name\":\"Manuela Gonçalves, A\"}]
datacite.creators.creator.creatorName.fl_str_mv Shahriari, S
Faria, S
Manuela Gonçalves, A
datacite.date.Accepted.fl_str_mv 2019-01-01T00:00:00Z
datacite.rights.fl_str_mv http://purl.org/coar/access_right/c_16ec
datacite.subjects.subject.fl_str_mv JackKnife
Outlier detection
Robust variable selection
Sparsity
datacite.titles.title.fl_str_mv A robust sparse linear approach for contaminated data
dc.creator.none.fl_str_mv Shahriari, S
Faria, S
Manuela Gonçalves, A
dc.date.Accepted.fl_str_mv 2019-01-01T00:00:00Z
dc.format.none.fl_str_mv application/pdf
dc.identifier.none.fl_str_mv https://hdl.handle.net/10216/149717
dc.language.none.fl_str_mv eng
dc.publisher.none.fl_str_mv Taylor & Francis
dc.rights.none.fl_str_mv http://purl.org/coar/access_right/c_16ec
dc.subject.none.fl_str_mv JackKnife
Outlier detection
Robust variable selection
Sparsity
dc.title.fl_str_mv A robust sparse linear approach for contaminated data
dc.type.none.fl_str_mv http://purl.org/coar/resource_type/c_6501
description A challenging problem in a linear regression model is to select a parsimonious model which is robust to the presence of contamination in the data. In this paper, we present a sparse linear approach which detects outliers by using a highly robust regression method. The model with optimal predictive ability as measured by the median absolute deviation of the prediction errors on JackKnife subsets is used to detect outliers. The performance of the proposed method is evaluated on a simulation study with a different type of outliers and high leverage points and also on a real data set.
dirty 0
eu_rights_str_mv restrictedAccess
format article
id rabertoup_4cc820bf79a7568ee670bc42e7e5fdfd
identifier.url.fl_str_mv https://hdl.handle.net/10216/149717
instacron_str UP
institution Universidade do Porto
instname_str Universidade do Porto
language eng
network_acronym_str rabertoup
network_name_str Repositório Aberto da Universidade do Porto
oai_identifier_str oai:repositorio-aberto.up.pt:10216/149717
organization_str_mv urn:organizationAcronym:up
person_str_mv Shahriari, S
Faria, S
Manuela Gonçalves, A
publishDate 2019
publisher.none.fl_str_mv Taylor & Francis
reponame_str Repositório Aberto da Universidade do Porto
repository_id_str urn:repositoryAcronym:rabertoup
service_str_mv urn:repositoryAcronym:rabertoup
spelling A challenging problem in a linear regression model is to select a parsimonious model which is robust to the presence of contamination in the data. In this paper, we present a sparse linear approach which detects outliers by using a highly robust regression method. The model with optimal predictive ability as measured by the median absolute deviation of the prediction errors on JackKnife subsets is used to detect outliers. The performance of the proposed method is evaluated on a simulation study with a different type of outliers and high leverage points and also on a real data set.application/pdfengTaylor & FrancisA robust sparse linear approach for contaminated dataShahriari, SFaria, SManuela Gonçalves, AHandlehttps://hdl.handle.net/10216/149717ISSNIsPartOf0361-0918ISSNIsPartOf1532-4141DOIIsPartOf10.1080/03610918.2019.158830420192019-01-01T00:00:00Zhttp://purl.org/coar/access_right/c_16ecrestricted accessJackKnifeOutlier detectionRobust variable selectionSparsity1818494 byteshttp://purl.org/coar/access_right/c_16ecapplication/pdffulltexthttps://repositorio-aberto.up.pt/bitstream/10216/149717/1/shahriari-cssc-2021.pdfliteraturehttp://purl.org/coar/resource_type/c_6501journal article
spellingShingle A robust sparse linear approach for contaminated data
Shahriari, S
JackKnife
Outlier detection
Robust variable selection
Sparsity
status SINGLETON
subject.fl_str_mv JackKnife
Outlier detection
Robust variable selection
Sparsity
title A robust sparse linear approach for contaminated data
title_full A robust sparse linear approach for contaminated data
title_fullStr A robust sparse linear approach for contaminated data
title_full_unstemmed A robust sparse linear approach for contaminated data
title_short A robust sparse linear approach for contaminated data
title_sort A robust sparse linear approach for contaminated data
topic JackKnife
Outlier detection
Robust variable selection
Sparsity
topic_facet JackKnife
Outlier detection
Robust variable selection
Sparsity
url https://hdl.handle.net/10216/149717
visible 1