Time-varying joint distribution through copulas

This paper deals with the analysis of temporal dependence in multivariate highfrequency time series data. The dependence structure between the marginal series is modelled through the use of copulas which, unlike the correlation matrix, give a complete description of the joint distribution. The marginal variances vary through time following univariate GARCH models. We develop full Bayesian inference where the whole set of model parameters is estimated simultaneously. This represents an essential difference with previous approaches in the literature where the marginal and the copula parameters are estimated separately in two consecutive steps. The proposed approach is illustrated with simulated data and a real bivariate time series on exchange rates. Key Words: Bayesian inference, copulas, multivariate GARCH, exchange rates. AMS subject classification: 62F15, 62M10

• Type: Journal
• Year: 2010
• Where: CSDA
• Authors: M. Concepcion Ausin, Hedibert F. Lopes
• Keywords: Bayesian Inference, CSDA 2010, Exchange Rates, Univariate Garch Models