Smoothing quantile regressions

Detalhes bibliográficos
Autor(a) principal: Fernandes, Marcelo
Data de Publicação: 2018
Outros Autores: Emmanuel, Guerre
Tipo de documento: Artigo de conferência
Idioma: eng
Título da fonte: Repositório Institucional do FGV (FGV Repositório Digital)
Texto Completo: https://hdl.handle.net/10438/27664
Resumo: We propose to smooth the entire objective function rather than only the check function in a linear quantile regression context. We derive a uniform Bahadur-Kiefer representation for the resulting convolution-type kernel estimator that demonstrates it improves on the extant quantile regression estimators in the literature. In addition, we also show that it is straightforward to compute asymptotic standard errors for the quantile regression coefficient estimates as well as to implement Wald-type tests. Simulations confirm that our smoothed quantile regression estimator performs very well in finite samples.
id FGV_f09a70733af59d561486267a250301bc
oai_identifier_str oai:repositorio.fgv.br:10438/27664
network_acronym_str FGV
network_name_str Repositório Institucional do FGV (FGV Repositório Digital)
repository_id_str 3974
spelling Fernandes, MarceloEmmanuel, GuerreDemais unidades::RPCA2019-07-03T14:57:45Z2019-07-03T14:57:45Z2018-04-08https://hdl.handle.net/10438/27664We propose to smooth the entire objective function rather than only the check function in a linear quantile regression context. We derive a uniform Bahadur-Kiefer representation for the resulting convolution-type kernel estimator that demonstrates it improves on the extant quantile regression estimators in the literature. In addition, we also show that it is straightforward to compute asymptotic standard errors for the quantile regression coefficient estimates as well as to implement Wald-type tests. Simulations confirm that our smoothed quantile regression estimator performs very well in finite samples.engAsymptotic expansionBahadur-Kiefer representationConditional quantileConvolution-based smoothingData-driven bandwidthRegressão quantílica linearEconomiaExpansões assintóticasAnálise de regressãoSmoothing quantile regressionsinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/conferenceObjectinfo:eu-repo/semantics/openAccessreponame:Repositório Institucional do FGV (FGV Repositório Digital)instname:Fundação Getulio Vargas (FGV)instacron:FGVRede de Pesquisa e Conhecimento AplicadoORIGINAL042_2018_Smoothing quantile regressions_MARCELO FERNANDES.PDF042_2018_Smoothing quantile regressions_MARCELO FERNANDES.PDFapplication/pdf501094https://repositorio.fgv.br/bitstreams/e8d7116f-a262-4cf2-9a71-abb5a11c72fe/download1bf60520cc6110ff3dddcefe8d918577MD51LICENSElicense.txtlicense.txttext/plain; charset=utf-84707https://repositorio.fgv.br/bitstreams/ab226b87-5f1d-4864-832c-5e1f2446bec1/downloaddfb340242cced38a6cca06c627998fa1MD52TEXT042_2018_Smoothing quantile regressions_MARCELO FERNANDES.PDF.txt042_2018_Smoothing quantile regressions_MARCELO FERNANDES.PDF.txtExtracted texttext/plain80428https://repositorio.fgv.br/bitstreams/95be944d-58f2-45bc-99cc-a54445baf961/downloadf574bbf0f7e07af1bad77b7c26576329MD55THUMBNAIL042_2018_Smoothing quantile regressions_MARCELO FERNANDES.PDF.jpg042_2018_Smoothing quantile regressions_MARCELO FERNANDES.PDF.jpgGenerated Thumbnailimage/jpeg3450https://repositorio.fgv.br/bitstreams/946e05a0-a85f-4fa4-90b1-1c43c626071b/downloadd3f75981f22f7be468ac6550546a52b9MD5610438/276642023-11-25 02:41:47.126open.accessoai:repositorio.fgv.br:10438/27664https://repositorio.fgv.brRepositório InstitucionalPRIhttp://bibliotecadigital.fgv.br/dspace-oai/requestopendoar:39742023-11-25T02:41:47Repositório Institucional do FGV (FGV Repositório Digital) - Fundação Getulio Vargas (FGV)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
dc.title.eng.fl_str_mv Smoothing quantile regressions
title Smoothing quantile regressions
spellingShingle Smoothing quantile regressions
Fernandes, Marcelo
Asymptotic expansion
Bahadur-Kiefer representation
Conditional quantile
Convolution-based smoothing
Data-driven bandwidth
Regressão quantílica linear
Economia
Expansões assintóticas
Análise de regressão
title_short Smoothing quantile regressions
title_full Smoothing quantile regressions
title_fullStr Smoothing quantile regressions
title_full_unstemmed Smoothing quantile regressions
title_sort Smoothing quantile regressions
author Fernandes, Marcelo
author_facet Fernandes, Marcelo
Emmanuel, Guerre
author_role author
author2 Emmanuel, Guerre
author2_role author
dc.contributor.unidadefgv.por.fl_str_mv Demais unidades::RPCA
dc.contributor.author.fl_str_mv Fernandes, Marcelo
Emmanuel, Guerre
dc.subject.eng.fl_str_mv Asymptotic expansion
Bahadur-Kiefer representation
Conditional quantile
Convolution-based smoothing
Data-driven bandwidth
topic Asymptotic expansion
Bahadur-Kiefer representation
Conditional quantile
Convolution-based smoothing
Data-driven bandwidth
Regressão quantílica linear
Economia
Expansões assintóticas
Análise de regressão
dc.subject.por.fl_str_mv Regressão quantílica linear
dc.subject.area.por.fl_str_mv Economia
dc.subject.bibliodata.por.fl_str_mv Expansões assintóticas
Análise de regressão
description We propose to smooth the entire objective function rather than only the check function in a linear quantile regression context. We derive a uniform Bahadur-Kiefer representation for the resulting convolution-type kernel estimator that demonstrates it improves on the extant quantile regression estimators in the literature. In addition, we also show that it is straightforward to compute asymptotic standard errors for the quantile regression coefficient estimates as well as to implement Wald-type tests. Simulations confirm that our smoothed quantile regression estimator performs very well in finite samples.
publishDate 2018
dc.date.issued.fl_str_mv 2018-04-08
dc.date.accessioned.fl_str_mv 2019-07-03T14:57:45Z
dc.date.available.fl_str_mv 2019-07-03T14:57:45Z
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
dc.type.driver.fl_str_mv info:eu-repo/semantics/conferenceObject
format conferenceObject
status_str publishedVersion
dc.identifier.uri.fl_str_mv https://hdl.handle.net/10438/27664
url https://hdl.handle.net/10438/27664
dc.language.iso.fl_str_mv eng
language eng
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.source.none.fl_str_mv reponame:Repositório Institucional do FGV (FGV Repositório Digital)
instname:Fundação Getulio Vargas (FGV)
instacron:FGV
instname_str Fundação Getulio Vargas (FGV)
instacron_str FGV
institution FGV
reponame_str Repositório Institucional do FGV (FGV Repositório Digital)
collection Repositório Institucional do FGV (FGV Repositório Digital)
bitstream.url.fl_str_mv https://repositorio.fgv.br/bitstreams/e8d7116f-a262-4cf2-9a71-abb5a11c72fe/download
https://repositorio.fgv.br/bitstreams/ab226b87-5f1d-4864-832c-5e1f2446bec1/download
https://repositorio.fgv.br/bitstreams/95be944d-58f2-45bc-99cc-a54445baf961/download
https://repositorio.fgv.br/bitstreams/946e05a0-a85f-4fa4-90b1-1c43c626071b/download
bitstream.checksum.fl_str_mv 1bf60520cc6110ff3dddcefe8d918577
dfb340242cced38a6cca06c627998fa1
f574bbf0f7e07af1bad77b7c26576329
d3f75981f22f7be468ac6550546a52b9
bitstream.checksumAlgorithm.fl_str_mv MD5
MD5
MD5
MD5
repository.name.fl_str_mv Repositório Institucional do FGV (FGV Repositório Digital) - Fundação Getulio Vargas (FGV)
repository.mail.fl_str_mv
_version_ 1810023800080695296

Registros relacionados