Even though an asset pricing model can be expressed in a classical Beta or in the relatively new stochastic discount factor (SDF) representation, their key empirical features - efficiency and robustness - may differ when estimated by the generalized method of moments. Using US and UK data we find that the SDF approach is more likely to be less efficient but more robust than Beta method. We derive the analytical asymptotic variance and show that the main drivers of this trade-o are the higher-order moments of the factors, in which skewness and covariance between returns and factors play an important role.
Keywords: Empirical Asset Pricing, Factor Models, Financial Econometrics, Generalized Method of Moments, Stochastic Discount Factor, Beta pricing, Efficiency.
JEL Classification: C51, C52, G12.