An approach to increasing forecast‐combination accuracy through VAR error modeling

Artikel

We consider a situation in which the forecaster has available M individual forecasts of a univariate target variable. We propose a 3-step procedure designed to exploit the interrelationships among the M forecast-error series (estimated from a large time-varying parameter VAR model of the errors, using past observations) with the aim of obtaining more accurate predictions of future forecast errors. The refined future forecast-error predictions are then used to obtain M new individual forecasts that are adapted to the information from the estimated VAR. The adapted M individual forecasts are ultimately combined and any potential accuracy gains from the adapted combination forecasts analyzed. We evaluate our approach in an out-of-sample forecasting analysis, using a well-established 7-country data set on output growth. Our 3-step procedure yields substantial accuracy gains (in terms of loss reductions of up to 18%) for the simple average and three time-varying-parameter combination forecasts.

Object Details

• Language: Englisch

References and Relationships

• Bibliographic citation: Journal: Journal of Forecasting ; ISSN: 1099-131X ; Volume: 40 ; Year: 2021 ; Issue: 4 ; Pages: 686-699 ; Hoboken, NJ: Wiley

Classification and Topics

• Subject: Bayesian VAR estimation ; dynamic model averaging ; forecast combinations ; forgetting factors ; large time‐varying parameter VARs ; state‐space model

Contributors, Places and Time

• Event: Geistige Schöpfung
• (who): Weigt, Till ; Wilfling, Bernd
• Event: Veröffentlichung
• (who): Wiley
• (where): Hoboken, NJ
• (when): 2021

Further information

• DOI: doi:10.1002/for.2733
• Handle: http://hdl.handle.net/10419/233668
• Last update: 10.03.2025, 11:44 AM CET