EconStor >
Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU) >
Institut für Wirtschaftspolitik und Quantitative Wirtschaftsforschung (IWQW), Universität Erlangen-Nürnberg >
IWQW Discussion Paper Series, FAU Erlangen-Nürnberg >

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

http://hdl.handle.net/10419/36698
  

Full metadata record

DC FieldValueLanguage
dc.contributor.authorSchlüter, Stephanen_US
dc.contributor.authorDeuschle, Carolaen_US
dc.date.accessioned2010-05-27en_US
dc.date.accessioned2010-07-20T14:04:20Z-
dc.date.available2010-07-20T14:04:20Z-
dc.date.issued2010en_US
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_US
dc.language.isoengen_US
dc.publisherUniv., Inst. für Wirtschaftspolitik und Quantitative Wirtschaftsforschung Erlangenen_US
dc.relation.ispartofseriesIWQW discussion paper series 04/2010en_US
dc.subject.jelC22en_US
dc.subject.jelC53en_US
dc.subject.ddc330en_US
dc.subject.keywordForecastingen_US
dc.subject.keywordWaveletsen_US
dc.subject.keywordARIMAen_US
dc.subject.keywordDenoisingen_US
dc.subject.keywordMultiscale Analysisen_US
dc.subject.stwZustandsraummodellen_US
dc.subject.stwZeitreihenanalyseen_US
dc.subject.stwPrognoseverfahrenen_US
dc.subject.stwTheorieen_US
dc.titleUsing wavelets for time series forecasting: Does it pay off?en_US
dc.typeWorking Paperen_US
dc.identifier.ppn626829879en_US
dc.rightshttp://www.econstor.eu/dspace/Nutzungsbedingungen-
dc.identifier.repecRePEc:zbw:iwqwdp:042010-
Appears in Collections:IWQW Discussion Paper Series, FAU Erlangen-Nürnberg

Files in This Item:
File Description SizeFormat
626829879.pdf247.36 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.