Bitte verwenden Sie diesen Link, um diese Publikation zu zitieren, oder auf sie als Internetquelle zu verweisen: https://hdl.handle.net/10419/36698 
Kompletter Metadatensatz
DublinCore-FeldWertSprache
dc.contributor.authorSchlüter, Stephanen
dc.contributor.authorDeuschle, Carolaen
dc.date.accessioned2010-05-27-
dc.date.accessioned2010-07-20T14:04:20Z-
dc.date.available2010-07-20T14:04:20Z-
dc.date.issued2010-
dc.identifier.urihttp://hdl.handle.net/10419/36698-
dc.description.abstractBy means of wavelet transform a time series can be decomposed into a time dependent sum of frequency components. As a result we are able to capture seasonalities with time-varying period and intensity, which nourishes the belief that incorporating the wavelet transform in existing forecasting methods can improve their quality. The article aims to verify this by comparing the power of classical and wavelet based techniques on the basis of four time series, each of them having individual characteristics. We find that wavelets do improve the forecasting quality. Depending on the data's characteristics and on the forecasting horizon we either favour a denoising step plus an ARIMA forecast or an multiscale wavelet decomposition plus an ARIMA forecast for each of the frequency components.en
dc.language.isoengen
dc.publisher|aFriedrich-Alexander-Universität Erlangen-Nürnberg, Institut für Wirtschaftspolitik und Quantitative Wirtschaftsforschung (IWQW) |cNürnbergen
dc.relation.ispartofseries|aIWQW Discussion Papers |x04/2010en
dc.subject.jelC22en
dc.subject.jelC53en
dc.subject.ddc330en
dc.subject.keywordForecastingen
dc.subject.keywordWaveletsen
dc.subject.keywordARIMAen
dc.subject.keywordDenoisingen
dc.subject.keywordMultiscale Analysisen
dc.subject.stwZustandsraummodellen
dc.subject.stwZeitreihenanalyseen
dc.subject.stwPrognoseverfahrenen
dc.subject.stwTheorieen
dc.titleUsing wavelets for time series forecasting: Does it pay off?-
dc.type|aWorking Paperen
dc.identifier.ppn626829879en
dc.rightshttp://www.econstor.eu/dspace/Nutzungsbedingungenen
dc.identifier.repecRePEc:zbw:iwqwdp:042010en

Datei(en):
Datei
Größe
247.36 kB





Publikationen in EconStor sind urheberrechtlich geschützt.