CFE 2015: Start Registration
View Submission - CFE
A0238
Title: Dynamic correlation models based on vines: The model and applications Authors:  Jean-David Fermanian - Ensae-Crest (France) [presenting]
Abstract: A new method for generating dynamics of conditional correlation matrices between asset returns is developed. These correlation matrices will be parameterized by their partial correlations, whose structure will be described by an oriented graph called ``vine''. Since partial correlation processes can be fitted and simulated separately, our approach is more parsimonious and flexible than other usual techniques, particularly the Dynamic Conditional Correlation family. We introduce a vine-GARCH class of processes and describe a quasi-maximum likelihood estimation procedure. We evaluate the performances of our models empirically and compare them with DCC-type specifications, through simulated experiments and by exploiting a database of daily stock returns.