A goodness-of-fit test for bivariate extreme-value copulas推荐.pdfVIP

Bernoulli 17(1), 2011, 253–275 DOI: 10.3150/10-BEJ279 A goodness-of-fit test for bivariate extreme-value copulas CHRISTIAN GENEST 1 , IVAN KOJADINOVIC2 , JOHANNA NEŠLEHOVÁ3 and JUN YAN4 1Département de mathématiques et de statistique, Université Laval, 1045, avenue de la Médecine, Québec, Canada G1V 0A6. E-mail: Christian.Genest@mat.ulaval.ca 2Laboratoire de mathématiques et applications, UMR CNRS 5142, Université de Pau et des Pays de l’Adour, Boîte postale 1155, 64013 Pau cedex, France. E-mail: Ivan.Kojadinovic@univ-pau.fr 3Department of Mathematics and Statistics, McGill University, 805, rue Sherbrooke Ouest, Montréal (Québec), Canada H3A 2K6. E-mail: Johanna.Neslehova@math.mcgill.ca 4Department of Statistics, University of Connecticut, 215 Glenbrook Road, Storrs, CT 06269, USA. E-mail: jun.yan@ It is often reasonable to assume that the dependence structure of a bivariate continuous distribution belongs to the class of extreme-value copulas. The latter are characterized by their Pickands dependence function. In this paper, a procedure is proposed for testing whether this function belongs to a given parametric fam- ily. The test is based on a Cramér–von Mises statistic measuring the distance between an estimate of the parametric Pickands dependence function and either one of two nonparametric estimators thereof studied by Genest and Segers [Ann. Statist. 37 (2009) 2990–3022]. As the limiting distribution of the test statistic depends on unknown parameters, it must be estimated via a parametric bootstrap procedure, the validity of which is established. Monte Carlo simulations are used to assess the power of the test and an extension to dependence structures that are left-tail decreasing in both variables is considered. Keywords: extreme-value copula; goodness of fit; parametric bootstrap; Pickands dependence function; rank-based inference 1. Introduction Let X and Y be continuous random variables with cumulative distribution fu