Chasing performance persistence of hedge funds – Comparative analysis of evaluation techniques

Abstract

We apply two complement methodologies (that is, stacked cross-sectional regression and quartile portfolio approach) in detecting the performance persistence of five different hedge fund styles. In addition, we compare the results obtained by using model-free performance metrics to those obtained by using both standard alphas of multifactor models and their empirical Bayesian counterparts. The results show that both the degree and existence of performance persistence vary among hedge fund styles and, in addition, depend on performance metric employed. Based on the combination of 3-year selection period and the subsequent 1-year holding period, model-free performance metrics (such as the Sharpe ratio and its downside risk-based variants) are more sensitive to detecting performance persistence than are factor-based performance metrics. Correspondingly, the prediction power of empirical Bayesian alphas is better than that of standard OLS alphas. The strongest evidence of performance persistence within the sample is among event-driven funds, for which 10 out of 12 persistence tests performed indicate significant results.