CMStatistics 2015: Start Registration
View Submission - CMStatistics
B1558
Topic: Contributed on Copula models and applications Title: Modelling the dependence structure between international financial returns using regime switching vine copula Authors:  Alex Donov - University of Essex (United Kingdom) [presenting]
Abstract: The dependence structure in international financial returns is modeled using second-order regime switching vine copula. Gaussian copula is used as a main building block in the vine specification where the dependence parameters are held constant within each regime. The model is applied to returns of the S$\&$P500, FTSE100 and DAX stock indices. The standard errors of the estimates are computed using Godambe information matrix. Empirically, regimes of high dependence are identified. The model is then compared against the benchmark model in which regime variable follows first-order process. Information criteria such as AIC and BIC suggest that the second-order regime switching model may be a good choice.