Skip navigation
Full metadata record
DC FieldValueLanguage
dc.contributor.authorHurvich, Clifford M.-
dc.date.accessioned2006-06-22T17:53:19Z-
dc.date.available2006-06-22T17:53:19Z-
dc.date.issued2000-
dc.identifier.urihttp://hdl.handle.net/2451/14794-
dc.description.abstractWe develop forecasting methodology for the fractional exponential (FEXP) model. First, we devise algorithms for fast exact computation of the coefficients in the infinite order autoregressive and moving average representations of a FEXP process. We also describe an algorithm to accurately approximate the autocovariances and to simulate realizations of the process. Next, we present a fast frequency-domain cross validation method for selecting the order of the model. This model selection method is designed to yield the model which provides the best multistep forecast for the given lead time, without assuming that the process actually obeys a FEXP model. Finally, we use the infinite order autoregressive coefficients of a fitted FEXP model to construct multistep forecasts of inflation in the United Kingdom. These forecasts are substantially different than those from a fitted ARFIMA model.en
dc.format.extent191796 bytes-
dc.format.mimetypeapplication/pdf-
dc.languageEnglishEN
dc.language.isoen
dc.publisherStern School of Business, New York Universityen
dc.relation.ispartofseriesSOR-2000-10en
dc.subjectFractional integrationen
dc.subjectLong-range dependenceen
dc.subjectSpectral factorizationen
dc.titleMultistep forecasting of long memory series using fractional exponential modelsen
dc.typeWorking Paperen
dc.description.seriesStatistics Working Papers SeriesEN
Appears in Collections:IOMS: Statistics Working Papers

Files in This Item:
File Description SizeFormat 
SOR-2000-10.pdf187.3 kBAdobe PDFView/Open


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