File Download
  Links for fulltext
     (May Require Subscription)
Supplementary

Article: New HSIC-based tests for independence between two stationary multivariate time series

TitleNew HSIC-based tests for independence between two stationary multivariate time series
Authors
KeywordsHilbert-Schmidt independence criterion
multivariate time series models
non-linear dependence
residual bootstrap
testing for independence
Issue Date2021
PublisherAcademia Sinica, Institute of Statistical Science. The Journal's web site is located at http://www.stat.sinica.edu.tw/statistica/
Citation
Statistica Sinica, 2021, v. 31, p. 269-300 How to Cite?
AbstractWe propose novel one-sided omnibus tests for independence between two multivariate stationary time series. These new tests apply the Hilbert-Schmidt independence criterion (HSIC) to test the independence between the innovations of the time series. We establish the limiting null distributions of our HSIC-based tests under regular conditions. Next, our HSIC-based tests are shown to be consistent. A residual bootstrap method is used to obtain the critical values for the tests, and its validity is justified. Existing cross-correlation-based tests examine linear dependence. In contrast, our tests examine general dependence (including linear and non-linear), providing researchers with information that is more complete on the causal relationship between two multivariate time series. The merits of our tests are illustrated using simulations and a real-data example.
Persistent Identifierhttp://hdl.handle.net/10722/305034
ISSN
2023 Impact Factor: 1.5
2023 SCImago Journal Rankings: 1.368
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorWang, G-
dc.contributor.authorLi, WK-
dc.contributor.authorZhu, K-
dc.date.accessioned2021-10-05T02:38:48Z-
dc.date.available2021-10-05T02:38:48Z-
dc.date.issued2021-
dc.identifier.citationStatistica Sinica, 2021, v. 31, p. 269-300-
dc.identifier.issn1017-0405-
dc.identifier.urihttp://hdl.handle.net/10722/305034-
dc.description.abstractWe propose novel one-sided omnibus tests for independence between two multivariate stationary time series. These new tests apply the Hilbert-Schmidt independence criterion (HSIC) to test the independence between the innovations of the time series. We establish the limiting null distributions of our HSIC-based tests under regular conditions. Next, our HSIC-based tests are shown to be consistent. A residual bootstrap method is used to obtain the critical values for the tests, and its validity is justified. Existing cross-correlation-based tests examine linear dependence. In contrast, our tests examine general dependence (including linear and non-linear), providing researchers with information that is more complete on the causal relationship between two multivariate time series. The merits of our tests are illustrated using simulations and a real-data example.-
dc.languageeng-
dc.publisherAcademia Sinica, Institute of Statistical Science. The Journal's web site is located at http://www.stat.sinica.edu.tw/statistica/-
dc.relation.ispartofStatistica Sinica-
dc.subjectHilbert-Schmidt independence criterion-
dc.subjectmultivariate time series models-
dc.subjectnon-linear dependence-
dc.subjectresidual bootstrap-
dc.subjecttesting for independence-
dc.titleNew HSIC-based tests for independence between two stationary multivariate time series-
dc.typeArticle-
dc.identifier.emailZhu, K: mazhuke@hku.hk-
dc.identifier.authorityZhu, K=rp02199-
dc.description.naturepublished_or_final_version-
dc.identifier.doi10.5705/ss.202018.0159-
dc.identifier.scopuseid_2-s2.0-85105812621-
dc.identifier.hkuros326288-
dc.identifier.volume31-
dc.identifier.spage269-
dc.identifier.epage300-
dc.identifier.isiWOS:000592923700012-
dc.publisher.placeTaiwan, Republic of China-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats