Wake Me Up Before You Go-Garch
Tinbergen Institute Discussion Paper No. 06-079/4
Posted: 22 Sep 2006
Date Written: September 2006
In this paper we present a new three-step approach to the estimation of Generalized Orthogonal GARCH (GO-GARCH) models, as proposed by van der Weide (2002). The approach only requires (non-linear) least-squares methods in combination with univariate GARCH estimation, and as such is computationally attractive, especially in larger-dimensional systems, where a full likelihood optimization is often infeasible. The effectiveness of the method is investigated using Monte Carlo simulations as well as a number of empirical applications.
Keywords: Multivariate GARCH; Non-Linear Least-Squares; Maximum Likelihood
JEL Classification: C13; C32
Suggested Citation: Suggested Citation