Shrinking Beta

Betas are used in many applications ranging from asset pricing tests, cost of capital estimation, investment management and risk management. Beta needs to be estimated, and to reduce estimation error, shrinkage to its cross-sectional average value of one is often applied. Since beta is the product of the return correlation of a security with the market and its relative return volatility to that of the market, we shrink correlation and volatility separately and evaluate its predictive power. We find economically and statistically significant gains from shrinking correlations more than volatilities