Testing unit root based on partially adaptive estimation

Detalhes bibliográficos
Autor(a) principal: Xiao, Zhijie
Data de Publicação: 2004
Outros Autores: Lima, Luiz Renato
Tipo de documento: Artigo
Idioma: eng
Título da fonte: Repositório Institucional do FGV (FGV Repositório Digital)
Texto Completo: http://hdl.handle.net/10438/887
Resumo: This paper proposes unit tests based on partially adaptive estimation. The proposed tests provide an intermediate class of inference procedures that are more efficient than the traditional OLS-based methods and simpler than unit root tests based on fully adptive estimation using nonparametric methods. The limiting distribution of the proposed test is a combination of standard normal and the traditional Dickey-Fuller (DF) distribution, including the traditional ADF test as a special case when using Gaussian density. Taking into a account the well documented characteristic of heavy-tail behavior in economic and financial data, we consider unit root tests coupled with a class of partially adaptive M-estimators based on the student-t distributions, wich includes te normal distribution as a limiting case. Monte Carlo Experiments indicate that, in the presence of heavy tail distributions or innovations that are contaminated by outliers, the proposed test is more powerful than the traditional ADF test. We apply the proposed test to several macroeconomic time series that have heavy-tailed distributions. The unit root hypothesis is rejected in U.S. real GNP, supporting the literature of transitory shocks in output. However, evidence against unit roots is not found in real exchange rate and nominal interest rate even haevy-tail is taken into a account.
id FGV_bbcdae8a6275c0396b19c1dd8f2f2bca
oai_identifier_str oai:repositorio.fgv.br:10438/887
network_acronym_str FGV
network_name_str Repositório Institucional do FGV (FGV Repositório Digital)
repository_id_str 3974
spelling Xiao, ZhijieLima, Luiz RenatoEscolas::EPGEFGV2008-05-13T15:39:13Z2008-05-13T15:39:13Z2004-03-010104-8910http://hdl.handle.net/10438/887This paper proposes unit tests based on partially adaptive estimation. The proposed tests provide an intermediate class of inference procedures that are more efficient than the traditional OLS-based methods and simpler than unit root tests based on fully adptive estimation using nonparametric methods. The limiting distribution of the proposed test is a combination of standard normal and the traditional Dickey-Fuller (DF) distribution, including the traditional ADF test as a special case when using Gaussian density. Taking into a account the well documented characteristic of heavy-tail behavior in economic and financial data, we consider unit root tests coupled with a class of partially adaptive M-estimators based on the student-t distributions, wich includes te normal distribution as a limiting case. Monte Carlo Experiments indicate that, in the presence of heavy tail distributions or innovations that are contaminated by outliers, the proposed test is more powerful than the traditional ADF test. We apply the proposed test to several macroeconomic time series that have heavy-tailed distributions. The unit root hypothesis is rejected in U.S. real GNP, supporting the literature of transitory shocks in output. However, evidence against unit roots is not found in real exchange rate and nominal interest rate even haevy-tail is taken into a account.engEscola de Pós-Graduação em Economia da FGVEnsaios Econômicos;528Testing unit root based on partially adaptive estimationinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleEconomiaEconomiaAnálise de séries temporaisEconometriareponame:Repositório Institucional do FGV (FGV Repositório Digital)instname:Fundação Getulio Vargas (FGV)instacron:FGVinfo:eu-repo/semantics/openAccessORIGINAL1549.pdfapplication/pdf312234https://repositorio.fgv.br/bitstreams/8162494d-aa2b-41ea-9dd9-2ddc37fc625f/downloadef978ff5fff41efedbdb126a489fe191MD51TEXT1549.pdf.txt1549.pdf.txtExtracted texttext/plain132531https://repositorio.fgv.br/bitstreams/549a61ed-1d0c-4a1d-b85c-4e6b1c8b050e/download8a2b5a49ca6b15d35cc9acd7e3e6ebf7MD56THUMBNAIL1549.pdf.jpg1549.pdf.jpgGenerated Thumbnailimage/jpeg3213https://repositorio.fgv.br/bitstreams/168c0b7b-e66b-42cf-9dfb-08292b9605a0/download8efab102488d948608476310187ed487MD5710438/8872023-11-09 21:52:59.483open.accessoai:repositorio.fgv.br:10438/887https://repositorio.fgv.brRepositório InstitucionalPRIhttp://bibliotecadigital.fgv.br/dspace-oai/requestopendoar:39742023-11-09T21:52:59Repositório Institucional do FGV (FGV Repositório Digital) - Fundação Getulio Vargas (FGV)false
dc.title.eng.fl_str_mv Testing unit root based on partially adaptive estimation
title Testing unit root based on partially adaptive estimation
spellingShingle Testing unit root based on partially adaptive estimation
Xiao, Zhijie
Economia
Economia
Análise de séries temporais
Econometria
title_short Testing unit root based on partially adaptive estimation
title_full Testing unit root based on partially adaptive estimation
title_fullStr Testing unit root based on partially adaptive estimation
title_full_unstemmed Testing unit root based on partially adaptive estimation
title_sort Testing unit root based on partially adaptive estimation
author Xiao, Zhijie
author_facet Xiao, Zhijie
Lima, Luiz Renato
author_role author
author2 Lima, Luiz Renato
author2_role author
dc.contributor.unidadefgv.por.fl_str_mv Escolas::EPGE
dc.contributor.affiliation.none.fl_str_mv FGV
dc.contributor.author.fl_str_mv Xiao, Zhijie
Lima, Luiz Renato
dc.subject.area.por.fl_str_mv Economia
topic Economia
Economia
Análise de séries temporais
Econometria
dc.subject.bibliodata.por.fl_str_mv Economia
Análise de séries temporais
Econometria
description This paper proposes unit tests based on partially adaptive estimation. The proposed tests provide an intermediate class of inference procedures that are more efficient than the traditional OLS-based methods and simpler than unit root tests based on fully adptive estimation using nonparametric methods. The limiting distribution of the proposed test is a combination of standard normal and the traditional Dickey-Fuller (DF) distribution, including the traditional ADF test as a special case when using Gaussian density. Taking into a account the well documented characteristic of heavy-tail behavior in economic and financial data, we consider unit root tests coupled with a class of partially adaptive M-estimators based on the student-t distributions, wich includes te normal distribution as a limiting case. Monte Carlo Experiments indicate that, in the presence of heavy tail distributions or innovations that are contaminated by outliers, the proposed test is more powerful than the traditional ADF test. We apply the proposed test to several macroeconomic time series that have heavy-tailed distributions. The unit root hypothesis is rejected in U.S. real GNP, supporting the literature of transitory shocks in output. However, evidence against unit roots is not found in real exchange rate and nominal interest rate even haevy-tail is taken into a account.
publishDate 2004
dc.date.issued.fl_str_mv 2004-03-01
dc.date.accessioned.fl_str_mv 2008-05-13T15:39:13Z
dc.date.available.fl_str_mv 2008-05-13T15:39:13Z
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
dc.type.driver.fl_str_mv info:eu-repo/semantics/article
format article
status_str publishedVersion
dc.identifier.uri.fl_str_mv http://hdl.handle.net/10438/887
dc.identifier.issn.none.fl_str_mv 0104-8910
identifier_str_mv 0104-8910
url http://hdl.handle.net/10438/887
dc.language.iso.fl_str_mv eng
language eng
dc.relation.ispartofseries.por.fl_str_mv Ensaios Econômicos;528
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.publisher.none.fl_str_mv Escola de Pós-Graduação em Economia da FGV
publisher.none.fl_str_mv Escola de Pós-Graduação em Economia da FGV
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/8162494d-aa2b-41ea-9dd9-2ddc37fc625f/download
https://repositorio.fgv.br/bitstreams/549a61ed-1d0c-4a1d-b85c-4e6b1c8b050e/download
https://repositorio.fgv.br/bitstreams/168c0b7b-e66b-42cf-9dfb-08292b9605a0/download
bitstream.checksum.fl_str_mv ef978ff5fff41efedbdb126a489fe191
8a2b5a49ca6b15d35cc9acd7e3e6ebf7
8efab102488d948608476310187ed487
bitstream.checksumAlgorithm.fl_str_mv 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_ 1813797866307584000