Please use this identifier to cite or link to this item: https://hdl.handle.net/10419/55186 
Full metadata record
DC FieldValueLanguage
dc.contributor.authorCarriero, Andreaen
dc.contributor.authorKapetanios, Georgeen
dc.contributor.authorMarcellino, Massimilianoen
dc.date.accessioned2012-02-09T14:07:09Z-
dc.date.available2012-02-09T14:07:09Z-
dc.date.issued2008-
dc.identifier.urihttp://hdl.handle.net/10419/55186-
dc.description.abstractModels based on economic theory have serious problems at forecasting exchange rates better than simple univariate driftless random walk models, especially at short horizons. Multivariate time series models suffer from the same problem. In this paper, we propose to forecast exchange rates with a large Bayesian VAR (BVAR), using a panel of 33 exchange rates vis-a-vis the US Dollar. Since exchange rates tend to co-move, the use of a large set of them can contain useful information for forecasting. In addition, we adopt a driftless random walk prior, so that cross-dynamics matter for forecasting only if there is strong evidence of them in the data. We produce forecasts for all the 33 exchange rates in the panel, and show that our model produces systematically better forecasts than a random walk for most of the countries, and at any forecast horizon, including at 1-step ahead.en
dc.language.isoengen
dc.publisher|aQueen Mary University of London, Department of Economics |cLondonen
dc.relation.ispartofseries|aWorking Paper |x634en
dc.subject.jelC53en
dc.subject.jelC11en
dc.subject.jelF31en
dc.subject.ddc330en
dc.subject.keywordexchange ratesen
dc.subject.keywordforecastingen
dc.subject.keywordBayesian VARen
dc.subject.stwWechselkursen
dc.subject.stwPrognoseen
dc.subject.stwVAR-Modellen
dc.subject.stwBayes-Statistiken
dc.subject.stwZeitreihenanalyseen
dc.subject.stwUSAen
dc.subject.stwWelten
dc.titleForecasting exchange rates with a large Bayesian VAR-
dc.typeWorking Paperen
dc.identifier.ppn583815499en
dc.rightshttp://www.econstor.eu/dspace/Nutzungsbedingungenen

Files in This Item:
File
Size
838.38 kB





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