Empirical Evaluation of Asset Pricing Models: A Comparison of the Sdf and Beta Methods

Abstract

The stochastic discount factor (SDF) method provides a unified general framework for econometric analysis of asset pricing models. It has recently been pointed out that the generality of the SDF method may come at the cost of estimation efficiency. We show that there is no need for this concern. The SDF method is as efficient as the classical beta method for estimating risk premia. In addition, the SDF method has an advantage -- the classical beta method, unlike the SDF method, substantially understates the effect of sampling errors when the estimated unanticipated changes in macroeconomic variables are used as pervasive factors.