Acceso usuarios
This paper sheds light on the evaluation of portfolio risk when portfolio variables are not normal, as is usually the case with financial variables. The methodology proposed in these cases is based on the assumption of a more general distribution capable of incorporating the behaviour of such variables, especially at the tails: the so called Edgeworth-Sargan distribution. this density is preferable over other distributions, such a the Student¿s t, when fitting high frequency financial variables, because of its flexibility for improving data fits ba adding more parameters in a natural way.
Furthermore, this distribution is easy to generalise to a multivariate context and, therefore, correlation coefficients among variables can be estimated efficiently. This article, therefore, provides new insights into VaR methodology by estimating the joint density of portfolio variables, and simultaneously calculating the right critical values of the underlying portfolio density. The empirical examples include the estiamation and evaluation of different portfolios composed of stock indices for major financial markets.
