EconStor >
Queen Mary, University of London >
School of Economics and Finance, Queen Mary, University of London  >
Working Paper Series, School of Economics and Finance, Queen Mary, University of London  >

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

http://hdl.handle.net/10419/55155
  

Full metadata record

DC FieldValueLanguage
dc.contributor.authorCarriero, Andreaen_US
dc.contributor.authorKapetanios, Georgeen_US
dc.contributor.authorMarcellino, Massimilianoen_US
dc.date.accessioned2010-08-04en_US
dc.date.accessioned2012-02-09T14:06:17Z-
dc.date.available2012-02-09T14:06:17Z-
dc.date.issued2010en_US
dc.identifier.urihttp://hdl.handle.net/10419/55155-
dc.description.abstractWe propose a new approach to forecasting the term structure of interest rates, which allows to efficiently extract the information contained in a large panel of yields. In particular, we use a large Bayesian Vector Autoregression (BVAR) with an optimal amount of shrinkage towards univariate AR models. Focusing on the U.S., we provide an extensive study on the forecasting performance of our proposed model relative to most of the existing alternative specifications. While most of the existing evidence focuses on statistical measures of forecast accuracy, we also evaluate the performance of the alternative forecasts when used within trading schemes or as a basis for portfolio allocation. We extensively check the robustness of our results via subsample analysis and via a data based Monte Carlo simulation. We find that: i) our proposed BVAR approach produces forecasts systematically more accurate than the random walk forecasts, though the gains are small; ii) some models beat the BVAR for a few selected maturities and forecast horizons, but they perform much worse than the BVAR in the remaining cases; iii) predictive gains with respect to the random walk have decreased over time; iv) different loss functions (i.e., statistical vs economic) lead to different ranking of specific models; v) modelling time variation in term premia is important and useful for forecasting.en_US
dc.language.isoengen_US
dc.publisherQueen Mary, Univ. of London, School of Economics and Finance Londonen_US
dc.relation.ispartofseriesWorking Paper // School of Economics and Finance, Queen Mary, University of London 662en_US
dc.subject.jelC11en_US
dc.subject.jelC53en_US
dc.subject.jelE43en_US
dc.subject.jelE47en_US
dc.subject.ddc330en_US
dc.subject.keywordBayesian methodsen_US
dc.subject.keywordforecastingen_US
dc.subject.keywordterm structureen_US
dc.subject.stwPrognoseverfahrenen_US
dc.subject.stwBayes-Statistiken_US
dc.subject.stwVAR-Modellen_US
dc.subject.stwZinsstrukturen_US
dc.titleForecasting government bond yields with large Bayesian VARsen_US
dc.typeWorking Paperen_US
dc.identifier.ppn63222813Xen_US
dc.rightshttp://www.econstor.eu/dspace/Nutzungsbedingungenen_US
Appears in Collections:Working Paper Series, School of Economics and Finance, Queen Mary, University of London

Files in This Item:
File Description SizeFormat
63222813X.pdf661.08 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.