Portfolio Management under Asymmetric Dependence and Distributio

Abstract

Aim of our paper is to analyze the enhancement of portfolio management by using more sophisticated assumptions about distributions and dependencies of stock returns. We assume a skewed t-distribution of the returns according to Azzalini and Capitanio (2003) and a dependency structure following a Clayton copula. The risk measure applied to our portfolio selection changed from traditional portfolio variance to downside-oriented conditional value-at-risk. The empirical results show a superior performance of our approach compared to the Markowitz approach and to the approach proposed by Hatherley and Alcock (2007) on a risk-adjusted basis. The approach is applied on daily stock returns of 16 stocks of the EURO STOXX 50.