Show simple item record

dc.contributor.authorFlorens, Jean-Pierre
dc.contributor.authorGouriéroux, Christian
dc.contributor.authorDarolles, Serge
dc.date.accessioned2012-05-04T14:26:26Z
dc.date.available2012-05-04T14:26:26Z
dc.date.issued2004-04
dc.identifier.urihttps://basepub.dauphine.fr/handle/123456789/9144
dc.language.isoenen
dc.subjectNonlinear canonical analysisen
dc.subjectKernel estimatorsen
dc.subjectReversibility hypothesisen
dc.subjectDiffusion equationsen
dc.subjectHigh-frequency dataen
dc.subject.ddc332en
dc.subject.classificationjelC14en
dc.subject.classificationjelC22en
dc.subject.classificationjelC40en
dc.titleKernel-based nonlinear canonical analysis and time reversibilityen
dc.typeArticle accepté pour publication ou publié
dc.description.abstractenWe consider a kernel-based approach to nonlinear canonical correlation analysis and its implementation for time series. We deduce a test procedure of the reversibility hypothesis. The method is applied to the analysis of stochastic differential equation from high-frequency data on stock returns.en
dc.relation.isversionofjnlnameJournal of Econometrics
dc.relation.isversionofjnlvol119en
dc.relation.isversionofjnlissue2en
dc.relation.isversionofjnldate2004-04
dc.relation.isversionofjnlpages323–353en
dc.relation.isversionofdoihttp://dx.doi.org/10.1016/S0304-4076(03)00199-4en
dc.description.sponsorshipprivateouien
dc.relation.isversionofjnlpublisherElsevieren
dc.subject.ddclabelEconomie financièreen


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record