Séminaire de Probabilités et Statistique
lundi 20 avril 2009 à 10:30 - UM2 - Bât 09 - Salle 331 (3ème ét.)
Michel Harel (Professeur à l'IUFM du Limousin, Université de Limoges, membre de l'Institut de Mathématiques de Toulouse)
"The marked empirical process to test nonlinear time series against a large class of alternatives when the random vectors are nonstationary and absolutely regular".
We study a procedure on goodness-of-fit testing for nonlinear time-series models against a large class of alternatives under nonstationarity and absolute regularity. For that, we define a marked process empirical process based on residuals which converges in distribution to a Gaussian process with respect to the Skorohod topology. This method was first introduced by Stute (1997) and then widely developped by Ngatchou-Wandji (2002, 2005, 2008) under more general conditions. Applications to general AR-ARCH models are given.