Predictive Regressions with Time-Varying Coefficients

77 Pages Posted: 17 Mar 2010 Last revised: 29 Sep 2011

See all articles by Thomas Dangl

Thomas Dangl

Vienna University of Technology

Michael Halling

University of Luxembourg

Multiple version iconThere are 3 versions of this paper

Date Written: September 29, 2011


We evaluate predictive regressions that explicitly consider the time-variation of coefficients in a comprehensive Bayesian framework. For monthly returns of the S&P 500 index, we demonstrate statistical as well as economic evidence of out-of-sample predictability: relative to an investor using the historic mean, an investor using our methodology could have earned consistently positive utility gains (between 1.8 and 5.8% p.a. over different time periods). We also find that predictive models with constant coefficients are dominated by models with time-varying coefficients. Finally, we show a strong link between out-of-sample predictability and the business cycle.

Keywords: Empirical asset pricing, equity return prediction, Bayesian econometrics

JEL Classification: G12, C11

Suggested Citation

Dangl, Thomas and Halling, Michael, Predictive Regressions with Time-Varying Coefficients (September 29, 2011). Available at SSRN: or

Thomas Dangl (Contact Author)

Vienna University of Technology ( email )

Theresianumgasse 27
Vienna, A-1040

Michael Halling

University of Luxembourg ( email )

L-1511 Luxembourg

Do you have negative results from your research you’d like to share?

Paper statistics

Abstract Views
PlumX Metrics