An Algorithmic Inference Approach to Learn Copulas

Abstract

We introduce a new method for estimating the parameter of the bivariate Clayton copulas within the framework of Algorithmic Inference. The method consists of a variant of the standard boot-strapping procedure for inferring random parameters, which we expressly devise to bypass the two pitfalls of this specific instance: the non independence of the Kendall statistics, customarily at the basis of this inference task, and the absence of a sufficient statistic w.r.t. \alpha. The variant is rooted on a numerical procedure in order to find the \alpha estimate at a fixed point of an iterative routine. Although paired with the customary complexity of the program which computes them, numerical results show an outperforming accuracy of the estimates.