Sometimes It's Better to Be Simple than Correct

Stephan Kolassa

Foresight: The International Journal of Applied Forecasting, 2016, issue 40, 20-26

Abstract: In the preceding article, Konstantinos Katsikopoulos and Aris Syntetos discussed the trade-offs between forecast bias and forecast variance in choosing a suitable forecasting method. Simple methods, they explain, tend to have large bias but low variance, while complexity reduces bias but at the expense of increasing variance. In short, simple methods might be preferable to complex methods, even if the resulting forecasts are biased. Stephan Kolassa now extends their argument to show that even if we know what the correct model is for the data to be forecast - that is, even if we know the seasonal pattern and other influencing factors for a time series - it may still be better to choose a simpler model, one that excludes one or more of these variables. This is a fascinating takeaway. Copyright International Institute of Forecasters, 2016

Date: 2016
References: Add references at CitEc
Citations: View citations in EconPapers (3)

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:2016:i:40:p:20-26

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 ().