Scandinavian Working Papers in Economics

Working Paper Series,
Sveriges Riksbank (Central Bank of Sweden)

No 191: Forecast Combination and Model Averaging using Predictive Measures

Jana Eklund () and Sune Karlsson ()
Additional contact information
Jana Eklund: Department of Economic Statistics, Postal: Stockholm School of Economics, PO Box 6501, SE-113 83 Stockholm, Sweden
Sune Karlsson: Department of Economics, Statistics and Informatics, Postal: Örebro University, SE-701 82 Örebro, Sweden

Abstract: We extend the standard approach to Bayesian forecast combination by forming the weights for the model averaged forecast from the predictive likelihood rather than the standard marginal likelihood. The use of predictive measures of fit offers greater protection against in-sample overfitting and improves forecast performance. For the predictive likelihood we show analytically that the forecast weights have good large and small sample properties. This is confirmed in a simulation study and an application to forecasts of the Swedish inflation rate where forecast combination using the predictive likelihood outperforms standard Bayesian model averaging using the marginal likelihood.

Keywords: Bayesian model averaging; Predictive likelihood; Partial Bayes factor; Training sample; Inflation rate

JEL-codes: C11; C51; C52

40 pages, September 1, 2005

Full text files

wp_191.pdf PDF-file 

Download statistics

Questions (including download problems) about the papers in this series should be directed to Lena Löfgren ()
Report other problems with accessing this service to Sune Karlsson ().

This page generated on 2018-01-23 23:37:31.