Do Forecasting Methods Reduce Avoidable Error? Evidence from Forecasting Competitions

Steve Morlidge

Foresight: The International Journal of Applied Forecasting, 2014, issue 32, 34-39

Abstract: The set of M-competitions Ð comparing the forecasting accuracy of two dozen common time series methods Ð is a landmark in our understanding of how different methods fare on a variety of data types. For example, one common procedure, the trend line extrapolation available in Excel, emerged as the least accurate of all, and probably should be considered a must to avoid. Yet, as Steve Morlidge tells us here, the implications for practitioners, especially demand forecasters, are not widely understood and quite possibly overlooked by most. Steve not only summarizes the key implications, he also uses a selection of data from the M3-Competition Ð the most recent (year 2000) and most comprehensive Ð to shed additional light on the bounds of forecastability: the best (and worst) forecast accuracy we can expect to achieve. Copyright International Institute of Forecasters, 2014

Date: 2014
References: Add references at CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
https://foresight.forecasters.org/shop/

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:for:ijafaa:y:2014:i:32:p:34-39

Access Statistics for this article

More articles in Foresight: The International Journal of Applied Forecasting from International Institute of Forecasters Contact information at EDIRC.
Bibliographic data for series maintained by Michael Gilliland ().