A regularized goodness-of-fit test for copulas

Christian Genest, Wanling Huang, Jean-Marie Dufour

Résumé


The authors propose an Anderson–Darling-type statistic for copula goodness-of-fit testing. They determine
the asymptotic distribution of the statistic under the null hypothesis. As this distribution depends on the unknown value
of the copula parameter, they call on a multiplier method to compute the p-value of the test. They assess the power of
the test through simulations and find that it is generally superior to that of the Cramér–von Mises statistic based on the
distance between the empirical copula and a consistent parametric copula estimate under H0.

Texte intégral : PDF


Creative Commons License
Ce travail est autorisé sous licence avec la Licence de paternité Creative Commons 3.0.

SFdS / SMF - Journal de la Société Française de Statistique - ISSN 2102-6238