Hessian Stochastic Ordering in the Family of multivariate Generalized Hyperbolic Distributions and its Applications

In this paper, random vectors following the multivariate generalized hyperbolic (GH) distribution are compared using the hessian stochastic order. This family includes the classes of symmetric and asymmetric distributions by which different behaviors of kurtosis in skewed and heavy tail data can be captured. By considering some closed convex cones and their duals, we derive some necessary and sufficient conditions for some important applied stochastic orderings. The linear convex orderings are shown to be equivalent with a certain kind of hessian orderings. Based on copulas generated by the GH distributions, it is revealed that the ordering of the GH distributions in terms of their dependence structures corresponds to some hessian stochastic orderings being satisfied. The results are shown to be relevant to some insurance and economic applications.