CMStatistics 2018: Start Registration
View Submission - CFE
Title: Asymptotics of Cholesky GARCH models and time-varying conditional betas Authors:  Christian Francq - CREST and University Lille III (France) [presenting]
Sebastien Laurent - AMU (France)
Serge Darolles - Paris Dauphine (France)
Abstract: A new model with time-varying slope coefficients is proposed. The model, called CHAR, is a Cholesky-GARCH model, based on a previous Cholesky decomposition of the conditional variance matrix introduced in the context of longitudinal data. We derive stationarity and invertibility conditions and prove consistency and asymptotic normality of the full and equation-by-equation QML estimators of this model. We then show that this class of models is useful to estimate conditional betas and compare it a previous approach, the dynamic conditional beta model. Finally, we use real data in a portfolio and risk management exercise. We find that the CHAR model outperforms a model with constant betas as well as the dynamic conditional beta model.