Feasible generalized least squares estimation of multivariate GARCH(1, 1) models

We provide a feasible generalized least squares estimator for (unrestricted) multivariate GARCH(1,1) models. We show that the estimator is consistent and asymptotically normally distributed under mild assumptions. Unlike the (quasi) maximum likelihood method, the feasible GLS is considerably fast to implement and does not require any complex optimization routine. We present numerical experiments on simulated data showing the performance of the GLS estimator, and discuss the limitations of our approach.