Chapter 4 Copula Theory Applied to Hedge Funds Dependence Structure Determination
Résumé
Purpose - In this chapter, copula theory is used to model dependence structure between hedge fund returns series. Methodology/approach - Goodness-of-fit tests, based on the Kendall's functions, are applied as selection criteria of the "best" copula. After estimating the parametric copula that best fits the used data, we apply previous results to construct the cumulative distribution functions of the equally weighted portfolios. Findings - The empirical validation shows that copula clearly allows better estimation of portfolio returns including hedge funds. The three studied portfolios reject the assumption of multivariate normality of returns. The chosen structure is often of Student type when only indices are considered. In the case of portfolios composed by only hedge funds, the dependence structure is of Franck type. Originality/value of the chapter - Introducing goodness-of-fit bootstrap method to validate the choice of the best structure of dependence is relevant for hedge fund portfolios. Copulas would be introduced to provide better estimations of performance measures.