EconStor >
Institut für Weltwirtschaft (IfW), Kiel >
Economics: The Open-Access, Open-Assessment E-Journal - Journal Articles >

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10419/18009
  

Full metadata record

DC FieldValueLanguage
dc.contributor.authorChen, Puen_US
dc.contributor.authorChihying, Hsiaoen_US
dc.date.accessioned2009-01-28T15:06:05Z-
dc.date.available2009-01-28T15:06:05Z-
dc.date.issued2007en_US
dc.identifier.citationEconomics: The Open-Access, Open-Assessment E-Journal 1 2007-11 1-43 doi:10.5018/economics-ejournal.ja.2007-11-
dc.identifier.pidoi:10.5018/economics-ejournal.ja.2007-11-
dc.identifier.urihttp://hdl.handle.net/10419/18009-
dc.description.abstractApplying a probabilistic causal approach, we define a class of time series causal models (TSCM) based on stationary Bayesian networks. A TSCM can be seen as a structural VAR identified by the causal relations among the variables. We classify TSCMs into observationally equivalent classes by providing a necessary and sufficient condition for the observational equivalence. Applying an automated learning algorithm, we are able to consistently identify the data-generating causal structure up to the class of observational equivalence. In this way we can characterize the empirical testable causal orders among variables based on their observed time series data. It is shown that while an unconstrained VAR model does not imply any causal orders in the variables, a TSCM that contains some empirically testable causal orders implies a restricted SVAR model. We also discuss the relation between the probabilistic causal concept presented in TSCMs and the concept of Granger causality. It is demonstrated in an application example that this methodology can be used to construct structural equations with causal interpretations.en_US
dc.language.isoengen_US
dc.publisherKiel Institute for the World Economy (IfW) Kielen_US
dc.relation.ispartofserieseconomics - The Open-Access, Open-Assessment E-Journal 2007-11en_US
dc.subject.jelC1en_US
dc.subject.ddc330en_US
dc.subject.keywordAutomated Learningen_US
dc.subject.keywordBayesian Networken_US
dc.subject.keywordInferred Causationen_US
dc.subject.keywordVARen_US
dc.subject.keywordWage-Price Spiralen_US
dc.subject.stwZeitreihenanalyseen_US
dc.subject.stwKausalanalyseen_US
dc.subject.stwVAR-Modellen_US
dc.subject.stwStatistische Methodeen_US
dc.titleLearning Causal Relations in Multivariate Time Series Dataen_US
dc.typeArticleen_US
dc.identifier.ppn540149861en_US
dc.identifier.urlhttp://www.economics-ejournal.org/economics/journalarticles/2007-11-
dc.rights.licensehttp://creativecommons.org/licenses/by-nc/2.0/de/deed.en-
dc.identifier.repecRePEc:zbw:ifweej:6175-
Appears in Collections:Economics: The Open-Access, Open-Assessment E-Journal - Journal Articles

Files in This Item:
File Description SizeFormat
economics_2007-11.pdf537.31 kBAdobe PDF
No. of Downloads: Counter Stats
Show simple item record
Download bibliographical data as: BibTeX

Items in EconStor are protected by copyright, with all rights reserved, unless otherwise indicated.