Short-term forecasting of electricity prices: Do we need a different model for each hour?

Adam Misiorek

No HSC/08/01, HSC Research Reports from Hugo Steinhaus Center, Wroclaw University of Science and Technology

Abstract: This empirical paper is a continuation of our earlier work on time series forecasting of day-ahead electricity prices. Given the controversy in the literature whether to use one large model across all hours or 24 separate models, we study if the model structure (and not only the coefficients) should change for different periods of the day. We find that leaving out the statistically insignificant factors leads to, on average, better point forecasts.

Keywords: Electricity price forecasting; Autoregression (AR) model; Threshold Autoregression (TAR) model (search for similar items in EconPapers)
JEL-codes: C22 C53 Q47 (search for similar items in EconPapers)
Pages: 10 pages
Date: 2008
References: View complete reference list from CitEc
Citations: View citations in EconPapers (10)

Published in MET (Medium Econometrische Toepassingen) 16.2 (2008) 8-13.

Downloads: (external link)
http://www.im.pwr.wroc.pl/~hugo/RePEc/wuu/wpaper/HSC_08_01.pdf Original draft, 2008 (application/pdf)
http://www.met-online.nl/pdf/MET16-2-2.pdf Final printed version, 2008 (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:wuu:wpaper:hsc0801

Access Statistics for this paper

More papers in HSC Research Reports from Hugo Steinhaus Center, Wroclaw University of Science and Technology Contact information at EDIRC.
Bibliographic data for series maintained by Rafal Weron (rafal.weron@pwr.edu.pl).