A0896
Title: An economic evaluation of exchange rates higher order moments timing
Authors: Francesco Violante - IESEG School of Management (France) [presenting]
Stefano Grassi - University of Rome 'Tor Vergata' (Italy)
Mattia Alfiero - University of Rome Tor Vergata (Italy)
Abstract: The sequential Monte Carlo and its online variant are proposed for the estimation of multivariate Garch models that feature time-varying skewness and kurtosis. Relative to model-specific Markov chain Monte Carlo, sequential Monte Carlo has the advantages of generality, parallelizability, and speed. Moreover, it gives as output the marginal likelihood useful in model selection. In the empirical application, the forecastability of the exchange rate is revisited through an asset allocation problem, using different specification of multivariate volatility models.
