RFS Advance Access published online on August 11, 2009
Review of Financial Studies, doi:10.1093/rfs/hhp063
Out-of-Sample Equity Premium Prediction: Combination Forecasts and Links to the Real Economy
Saint Louis University
Saint Louis University
Washington University in St. Louis
Send correspondence to Guofu Zhou, Olin School of Business, Washington University in St. Louis, St. Louis, MO 63130; telephone: 314-935-6384; fax: 314-935-6359. E-mail: zhou{at}wustl.edu
JEL Classification: C22, C53, G11, G12
 |
Abstract |
|---|
Welch and Goyal (2008) find that numerous economic variables with in-sample predictive ability for the equity premium fail to deliver consistent out-of-sample forecasting gains relative to the historical average. Arguing that model uncertainty and instability seriously impair the forecasting ability of individual predictive regression models, we recommend combining individual forecasts. Combining delivers statistically and economically significant out-of-sample gains relative to the historical average consistently over time. We provide two empirical explanations for the benefits of forecast combination: (i) combining forecasts incorporates information from numerous economic variables while substantially reducing forecast volatility; (ii) combination forecasts are linked to the real economy.
We are grateful to Andrew Ang, John Campbell, Long Chen, Ethan Chiang, John Cochrane, Hui Guo, Michael Halling, Yufeng Han, Campbell Harvey, Huiyu Huang, Ravi Jagannathan, Raymond Kan, Augio Kong, Sydney Ludvigson, Mike McCracken,
ubo
Pástor, Jun Tu, and seminar participants at McGill University, Singapore Management University, Tsinghua University, Washington University, and the Missouri Economics Conference for helpful comments. We are also especially grateful to an anonymous referee for valuable comments that helped to substantially improve the paper, as well as Matthew Spiegel (the Executive Editor) for insightful comments that led to the paper's investigation of links to the real economy. Rapach and Strauss acknowledge financial support from the Simon Center for Regional Forecasting at Saint Louis University. This paper supersedes an earlier version that circulated under the title "Out-of-Sample Equity Premium Prediction: Consistently Beating the Historical Average," originally dated 23 July 2007.