On the maximization of financial performance measures within mixture models

Abstract : We introduce mixtures of probability distributions to model empirical distributions of financial asset returns. In this framework, we examine the problem of maximizing performance measures. For this purpose, we consider a large class of reward/risk ratios such as the Kappa measures and in particular the Omega ratio. This latter measure is associated to a downside risk measure based on a put component. All these measures can take account of the asymmetry of the probability distribution, which is important when dealing with mixture of distributions. We examine first a fundamental example: the ranking and maximization of Gaussian mixture distributions, according to the Omega performance measure. Then we provide a general result for the maximization of mixture distributions with respect to a very large family of performance measures, including Kappa measures.
Type de document :
Article dans une revue
Statistics & Decisions, 2011, 28 (1), pp.63-80. 〈10.1524/stnd.2011.1083〉
Liste complète des métadonnées

https://hal-paris1.archives-ouvertes.fr/hal-00608960
Contributeur : Rania Hentati Kaffel <>
Soumis le : samedi 16 juillet 2011 - 13:33:17
Dernière modification le : jeudi 3 mai 2018 - 15:18:04

Identifiants

Collections

Citation

Rania Hentati, Jean-Luc Prigent. On the maximization of financial performance measures within mixture models. Statistics & Decisions, 2011, 28 (1), pp.63-80. 〈10.1524/stnd.2011.1083〉. 〈hal-00608960〉

Partager

Métriques

Consultations de la notice

179