The goal of this paper is to propose inference methods for regime switching copula models. We present an algorithm for the estimation of parameters and we propose a goodness-of-fit test for the adequacy of these models. More precisely, it is assumed that we have a multivariate time series, and for each univariate time series, we fit a generalized error model, producing estimations of independent error terms. In fact, we assume that the copula associated with the error terms is a regime-switching copula. We show how to estimate the parameters of the model copula and we propose a goodness-of-fit test. The latter is then used to select the number of regimes. An application is proposed to evaluate an European put-on-max option on the returns of two assests. Finally, in order to facilitate the use of our methodology, we have built a R package HMMcopula which is available on CRAN.
Published December 2018 , 16 pages