A Style-Based Market Risk Model for Hedge Fund Portfolios

Abstract

In this article, the authors develop a market risk model for hedge fund portfolios by integrating cluster analysis, extreme value theory (EVT), and copula modeling. Because the cluster model is exclusively based on fund returns, cluster classifications are more objective than self-reported styles. The EVT contribution considers the fat-tailed distribution of hedge fund returns, implicitly accounting for jump risk. The copula method accounts for the dependence between clusters. Two Gumbel copulas are constructed—one on the average returns of funds in the clusters, and the other on returns of all funds in the clusters. The first copula is directly applicable to a highly diversified portfolio and the authors show how to apply this copula to a general hedge fund portfolio. The second copula is suitable for simulations on nondiversified portfolios and also provides a tool for stress tests. Monte Carlo simulations indicate that investing in a broadly diversified hedge fund portfolio is not riskier than investing in a traditional diversified portfolio.