Multivariate Variance Targeting in the BEKK-GARCH Model
34 Pages Posted: 21 Nov 2012
Date Written: November 14, 2012
This paper considers asymptotic inference in the multivariate BEKK model based on (co-)variance targeting (VT). By de finition the VT estimator is a two-step estimator and the theory presented is based on expansions of the modifi ed likelihood function, or estimating function, corresponding to these two steps. Strong consistency is established under weak moment conditions, while sixth order moment restrictions are imposed to establish asymptotic normality. Included simulations indicate that the multivariately induced higher order moment constraints are indeed necessary.
Suggested Citation: Suggested Citation