Model Uncertainty and Systematic Risk in US Banking

This paper uses Bayesian model averaging (BMA) techniques to examine the driving factors of equity returns of U.S. financial institutions. The main advantage of BMA is accounting for model uncertainty. For the period 1986-2010, we fi nd that the most likely model explaining banking sector returns has a probability of 25% only. We also show that the optimal model changes considerably over time and across types of BHCs. The market, high-minus-low (HML) Fama-French factor, and real estate factor are part of most speci fications. Finally, we highlight some implications for banking studies using measures of idiosyncratic volatility, abnormal returns for market betas