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
  
Title:Using wavelets for time series forecasting: Does it pay off? PDF Logo
Authors:Schlüter, Stephan
Deuschle, Carola
Issue Date:2010
Series/Report no.:IWQW discussion paper series 04/2010
Abstract:By 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.
Subjects:Forecasting
Wavelets
ARIMA
Denoising
Multiscale Analysis
JEL:C22
C53
Document Type:Working Paper
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
Download bibliographical data as: BibTeX
Share on:http://hdl.handle.net/10419/36698

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