Multifactor risk loadings and abnormal returns under uncertainty and learning

We explore the time variation of factor loadings and abnormal returns in the context of a four-factor model. Our methodology, based on an application of the Kalman filter and on endogenous uncertainty, overcomes several limitations of competing approaches used in the literature. Besides taking learning into account, it does not rely on any conditioning information, and it only imposes minimal assumptions on the time variation of the parameters. Our estimates capture both short- and long-term fluctuations of risk loadings and abnormal returns, also showing marked variation across US industry portfolios. The results from mean-variance spanning tests indicate that our baseline model yields accurate predictions and can therefore improve pricing and performance measurement.