The (Poor) Predictive Performance of Asset Pricing Models

Posted: 4 Oct 2006

Abstract

This paper examines time-series forecast errors of expected returns from conditional and unconditional asset pricing models for portfolio and individual firm equity returns. A new result concerning model specification and forecasting that increases predictive precision is introduced. Conditional versions of the models generally produce higher mean squared errors than unconditional versions for step-ahead prediction. This holds for individual firm data when the instruments are firm specific. Mean square forecast error decompositions indicate that the asset pricing models produce relatively unbiased predictions, but the variance is severe enough to ruin the step ahead predictive ability beyond that of a constant benchmark.

Keywords: Out-of-sample, prediction, mean square error

JEL Classification: G12, C53, E37

Suggested Citation

Simin, Timothy T., The (Poor) Predictive Performance of Asset Pricing Models. Journal of Financial and Quantitative Analysis, Forthcoming, Available at SSRN: https://ssrn.com/abstract=934727

Timothy T. Simin (Contact Author)

Pennsylvania State University ( email )

University Park, PA 16802
United States
814-865-3457 (Phone)

HOME PAGE: http://timsimin.net

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

Paper statistics

Abstract Views
971
PlumX Metrics