Influence of information criteria choice on the proportion of non-rejection of the null hypothesis of the ADF test considering the presence of unit roots

Detalhes bibliográficos
Autor(a) principal: Silveira, Anderson
Data de Publicação: 2023
Outros Autores: Coelho Amaral, Mariane, Leite Dias de Mattos, Viviane, Nakamura, Luiz Ricardo, Konrath, Andrea Cristina
Tipo de documento: Artigo
Idioma: por
Título da fonte: Vetor (Online)
Texto Completo: https://periodicos.furg.br/vetor/article/view/15163
Resumo: One of the various techniques used for time series analysis is econometric analysis, where in many cases it is necessary to verify the stationarity of the series. A non-stationary series presents the presence of unit roots, which makes it unsuitable for making forecasts. In this context, the so-called unit root tests have emerged, among which the Augmented Dickey-Fuller (ADF) test stands out. One of the crucial steps in applying the ADF test is the selection of lags. To select the lags to be applied in the test, it is necessary to define a maximum number from which the ideal number to be used in the ADF application will be selected. This ideal number can be determined with the aid of information criteria, such as the traditional AIC, BIC, and HQC. This study evaluated the influence of the choice of information criteria on the test result, considering the presence of unit roots. After the construction of scenarios, application of tests, and analysis of variance, no evidence was found that the choice of information criteria can interfere with the rate of non-rejection of the null hypothesis in the ADF test.
id FURG-7_c31ee734496d1c04689c71670af8e613
oai_identifier_str oai:ojs.periodicos.furg.br:article/15163
network_acronym_str FURG-7
network_name_str Vetor (Online)
repository_id_str
spelling Influence of information criteria choice on the proportion of non-rejection of the null hypothesis of the ADF test considering the presence of unit rootsInfluência da escolha do critério de informação na proporção de não rejeição da hipótese nula do teste ADF considerando a presença de raiz unitáriaUnit root testInformation CriteriaADFLag selectionUnit rootTime seriesTeste de raiz unitáriaCritério de InformaçãoADFSeleção de defasagensRaiz unitáriaSéries temporaisOne of the various techniques used for time series analysis is econometric analysis, where in many cases it is necessary to verify the stationarity of the series. A non-stationary series presents the presence of unit roots, which makes it unsuitable for making forecasts. In this context, the so-called unit root tests have emerged, among which the Augmented Dickey-Fuller (ADF) test stands out. One of the crucial steps in applying the ADF test is the selection of lags. To select the lags to be applied in the test, it is necessary to define a maximum number from which the ideal number to be used in the ADF application will be selected. This ideal number can be determined with the aid of information criteria, such as the traditional AIC, BIC, and HQC. This study evaluated the influence of the choice of information criteria on the test result, considering the presence of unit roots. After the construction of scenarios, application of tests, and analysis of variance, no evidence was found that the choice of information criteria can interfere with the rate of non-rejection of the null hypothesis in the ADF test.Dentre as diversas técnicas utilizadas para a análise de séries temporais está a análise econométrica, onde em muitos casos é necessário verificar a estacionariedade da série. Uma série não estacionária apresenta a presença de raiz unitária, o que faz com que não seja adequada para realizar previsões. Nesse contexto, surgiram os denominados testes de raiz unitária, dentre os quais cabe destacar o teste de Dickey-Fuller Aumentado (ADF). Uma das etapas de grande importância na aplicação do teste ADF é a seleção de defasagens. Para selecionar as defasagens a serem aplicadas no teste, é necessário definir um número máximo, a partir do qual será selecionado o número ideal que será utilizado na aplicação do ADF. Este número ideal pode ser determinado com o auxílio dos critérios de informação, como por exemplo os tradicionais AIC, BIC e HQC. Este trabalho avaliou a influência da escolha do critério de informação no resultado do teste, considerando a presença de raiz unitária. Após a construção dos cenários, aplicação dos testes, e realização de análise de variância, não foram encontrados indícios que a escolha do critério de informação possa interferir na taxa de não rejeição da hipótese nula no teste ADF.Universidade Federal do Rio Grande2023-12-23info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionapplication/pdfhttps://periodicos.furg.br/vetor/article/view/1516310.14295/vetor.v33i2.15163VETOR - Journal of Exact Sciences and Engineering; Vol. 33 No. 2 (2023); 11-16VETOR - Revista de Ciências Exatas e Engenharias; v. 33 n. 2 (2023); 11-162358-34520102-7352reponame:Vetor (Online)instname:Universidade Federal do Rio Grande (FURG)instacron:FURGporhttps://periodicos.furg.br/vetor/article/view/15163/10459Copyright (c) 2023 VETOR - Revista de Ciências Exatas e Engenhariasinfo:eu-repo/semantics/openAccessSilveira, AndersonCoelho Amaral, MarianeLeite Dias de Mattos, VivianeNakamura, Luiz RicardoKonrath, Andrea Cristina2023-12-23T15:36:55Zoai:ojs.periodicos.furg.br:article/15163Revistahttps://periodicos.furg.br/vetorPUBhttps://periodicos.furg.br/vetor/oaigmplatt@furg.br2358-34520102-7352opendoar:2023-12-23T15:36:55Vetor (Online) - Universidade Federal do Rio Grande (FURG)false
dc.title.none.fl_str_mv Influence of information criteria choice on the proportion of non-rejection of the null hypothesis of the ADF test considering the presence of unit roots
Influência da escolha do critério de informação na proporção de não rejeição da hipótese nula do teste ADF considerando a presença de raiz unitária
title Influence of information criteria choice on the proportion of non-rejection of the null hypothesis of the ADF test considering the presence of unit roots
spellingShingle Influence of information criteria choice on the proportion of non-rejection of the null hypothesis of the ADF test considering the presence of unit roots
Silveira, Anderson
Unit root test
Information Criteria
ADF
Lag selection
Unit root
Time series
Teste de raiz unitária
Critério de Informação
ADF
Seleção de defasagens
Raiz unitária
Séries temporais
title_short Influence of information criteria choice on the proportion of non-rejection of the null hypothesis of the ADF test considering the presence of unit roots
title_full Influence of information criteria choice on the proportion of non-rejection of the null hypothesis of the ADF test considering the presence of unit roots
title_fullStr Influence of information criteria choice on the proportion of non-rejection of the null hypothesis of the ADF test considering the presence of unit roots
title_full_unstemmed Influence of information criteria choice on the proportion of non-rejection of the null hypothesis of the ADF test considering the presence of unit roots
title_sort Influence of information criteria choice on the proportion of non-rejection of the null hypothesis of the ADF test considering the presence of unit roots
author Silveira, Anderson
author_facet Silveira, Anderson
Coelho Amaral, Mariane
Leite Dias de Mattos, Viviane
Nakamura, Luiz Ricardo
Konrath, Andrea Cristina
author_role author
author2 Coelho Amaral, Mariane
Leite Dias de Mattos, Viviane
Nakamura, Luiz Ricardo
Konrath, Andrea Cristina
author2_role author
author
author
author
dc.contributor.author.fl_str_mv Silveira, Anderson
Coelho Amaral, Mariane
Leite Dias de Mattos, Viviane
Nakamura, Luiz Ricardo
Konrath, Andrea Cristina
dc.subject.por.fl_str_mv Unit root test
Information Criteria
ADF
Lag selection
Unit root
Time series
Teste de raiz unitária
Critério de Informação
ADF
Seleção de defasagens
Raiz unitária
Séries temporais
topic Unit root test
Information Criteria
ADF
Lag selection
Unit root
Time series
Teste de raiz unitária
Critério de Informação
ADF
Seleção de defasagens
Raiz unitária
Séries temporais
description One of the various techniques used for time series analysis is econometric analysis, where in many cases it is necessary to verify the stationarity of the series. A non-stationary series presents the presence of unit roots, which makes it unsuitable for making forecasts. In this context, the so-called unit root tests have emerged, among which the Augmented Dickey-Fuller (ADF) test stands out. One of the crucial steps in applying the ADF test is the selection of lags. To select the lags to be applied in the test, it is necessary to define a maximum number from which the ideal number to be used in the ADF application will be selected. This ideal number can be determined with the aid of information criteria, such as the traditional AIC, BIC, and HQC. This study evaluated the influence of the choice of information criteria on the test result, considering the presence of unit roots. After the construction of scenarios, application of tests, and analysis of variance, no evidence was found that the choice of information criteria can interfere with the rate of non-rejection of the null hypothesis in the ADF test.
publishDate 2023
dc.date.none.fl_str_mv 2023-12-23
dc.type.driver.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
format article
status_str publishedVersion
dc.identifier.uri.fl_str_mv https://periodicos.furg.br/vetor/article/view/15163
10.14295/vetor.v33i2.15163
url https://periodicos.furg.br/vetor/article/view/15163
identifier_str_mv 10.14295/vetor.v33i2.15163
dc.language.iso.fl_str_mv por
language por
dc.relation.none.fl_str_mv https://periodicos.furg.br/vetor/article/view/15163/10459
dc.rights.driver.fl_str_mv Copyright (c) 2023 VETOR - Revista de Ciências Exatas e Engenharias
info:eu-repo/semantics/openAccess
rights_invalid_str_mv Copyright (c) 2023 VETOR - Revista de Ciências Exatas e Engenharias
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv Universidade Federal do Rio Grande
publisher.none.fl_str_mv Universidade Federal do Rio Grande
dc.source.none.fl_str_mv VETOR - Journal of Exact Sciences and Engineering; Vol. 33 No. 2 (2023); 11-16
VETOR - Revista de Ciências Exatas e Engenharias; v. 33 n. 2 (2023); 11-16
2358-3452
0102-7352
reponame:Vetor (Online)
instname:Universidade Federal do Rio Grande (FURG)
instacron:FURG
instname_str Universidade Federal do Rio Grande (FURG)
instacron_str FURG
institution FURG
reponame_str Vetor (Online)
collection Vetor (Online)
repository.name.fl_str_mv Vetor (Online) - Universidade Federal do Rio Grande (FURG)
repository.mail.fl_str_mv gmplatt@furg.br
_version_ 1797041760265830400

Registros relacionados