Predictive Gains from Forecast Combinations Using Time Varying Model Weights

41 Pages Posted: 11 Sep 2007

See all articles by Francesco Ravazzolo

Francesco Ravazzolo

Free University of Bolzano

Marno Verbeek

Erasmus University - Rotterdam School of Management; Erasmus Research Institute of Management (ERIM); Netspar

H. K. van Dijk

Tinbergen Institute; Econometric Institute

Date Written: August 2007

Abstract

Several frequentist and Bayesian model averaging schemes, including a new one that simultaneously allows for parameter uncertainty, model uncertainty and time varying model weights, are compared in terms of forecast accuracy over a set of simulation experiments. Artificial data are generated, characterized by low predictability, structural instability, and fat tails, which is typical for many financial-economic time series. Sensitivity of results with respect to misspecification of the number of included predictors and the number of included models is explored. Given the set up of our experiments, time varying model weight schemes outperform other averaging schemes in terms of predictive gains both when the correlation among individual forecasts is low and the underlying data generating process is subject to structural locations shifts. In an empirical application using returns on the S&P 500 index, time varying model weights provide improved forecasts with substantial economic gains in an investment strategy including transaction costs.

Keywords: Stock return predictability, time varying weight combination, forecast combination, Bayesian model averaging

JEL Classification: C11, C53, G11

Suggested Citation

Ravazzolo, Francesco and Verbeek, Marno and van Dijk, Herman K., Predictive Gains from Forecast Combinations Using Time Varying Model Weights (August 2007). Available at SSRN: https://ssrn.com/abstract=1012574 or http://dx.doi.org/10.2139/ssrn.1012574

Francesco Ravazzolo (Contact Author)

Free University of Bolzano ( email )

Bolzano
Italy

Marno Verbeek

Erasmus University - Rotterdam School of Management ( email )

P.O. Box 1738
Room T09-53
3000 DR Rotterdam
Netherlands
+31 10 408 2790 (Phone)

HOME PAGE: http://www.rsm.nl/mverbeek

Erasmus Research Institute of Management (ERIM)

P.O. Box 1738
3000 DR Rotterdam
Netherlands

Netspar

P.O. Box 90153
Tilburg, 5000 LE
Netherlands

Herman K. Van Dijk

Tinbergen Institute ( email )

Gustav Mahlerplein 117
Burg. Oudlaan 50
Amsterdam/Rotterdam, 1082 MS
Netherlands
+31104088955 (Phone)
+31104089031 (Fax)

HOME PAGE: http://people.few.eur.nl/hkvandijk/

Econometric Institute ( email )

P.O. Box 1738
3000 DR Rotterdam
Netherlands
+31 10 4088955 (Phone)
+31 10 4527746 (Fax)

Register to save articles to
your library

Register

Paper statistics

Downloads
288
Abstract Views
1,289
rank
105,501
PlumX Metrics