A Conditional Approach to Hedge Fund Risk

Abstract

In this study, we apply a two-step conditional Bayesian approach to hedge fund risk. In the first step, a mixture of two normal distributions is estimated for a core asset, one distribution being identified as linked to a quiet regime, the other one to a hectic regime. The conditional probabilities of each regime are then inferred and a mixture of distributions is deduced for peripheral assets. In our application, the core asset is alternatively chosen as the S&P index or the Baa/Treasuries yield spread and the peripheral assets are the major hedge funds strategies over the period 1990-2004. The methodology has several advantages given specific features of hedge funds returns, notably non- linear exposure to standard assets returns and short sample history. We identify significant changes in the distribution (mean and standard deviation) of hedge fund returns across regimes. Results are less clear-cut for the correlation with standard assets, as modifications can be imputed to a certain extent to a form of selection bias. We finally present an application of the methodology for stress tests on hedge funds portfolios.