Show simple item record

dc.contributor.authorPesaran, M. Hashem
dc.contributor.authorPettenuzzo, Davide
dc.contributor.authorTimmermann, Allan
dc.date.accessioned2004-06-24T08:43:29Z
dc.date.available2004-06-24T08:43:29Z
dc.date.issued2004-06
dc.identifier.otherCWPE0433
dc.identifier.urihttp://www.dspace.cam.ac.uk/handle/1810/444
dc.identifier.urihttps://www.repository.cam.ac.uk/handle/1810/444
dc.description.abstractThis paper provides a novel approach to forecasting time series subject to discrete structural breaks. We propose a Bayesian estimation and prediction procedure that allows for the possibility of new breaks over the forecast horizon, taking account of the size and duration of past breaks (if any) by means of a hierarchical hidden Markov chain model. Predictions are formed by integrating over the hyper parameters from the meta distributions that characterise the stochastic break point process. In an application to US Treasury bill rates, we find that the method leads to better out-of-sample forecasts than alternative methods that ignore breaks, particularly at long horizons.en_GB
dc.format.extent255230 bytes
dc.format.mimetypeapplication/pdf
dc.language.isoen
dc.publisherFaculty of Economics
dc.relation.ispartofseriesCambridge Working Papers in Economics
dc.rightsAll Rights Reserveden
dc.rights.urihttps://www.rioxx.net/licenses/all-rights-reserved/en
dc.subjectstructural breaks, forecasting, hierarchical hidden Markov Chain model, Bayesian model averagingen_GB
dc.titleForecasting Time Series Subject to Multiple Structural Breaksen_GB
dc.typeWorking Paperen
dc.identifier.doi10.17863/CAM.5112


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record