Title: On copulas constructed with Bernoulli and Coxian-2 distributions
Authors: Christopher Blier-Wong - Université Laval (Canada) [presenting]
Abstract: A new generalized Farlie-Gumbel-Morgenstern copula is constructed that naturally scales to high dimensions. The copula can model moderate positive and negative dependence, can cover different types of asymmetries and admits exact expressions for many quantities of interest, such as measures of association or risk measures in actuarial science. We construct this copula through a stochastic representation based on multivariate Bernoulli random vectors and Coxian-2 distributions. The construction of the copula and the study of its measures of multivariate association and stochastic ordering is addressed. We explain how to sample random vectors in high dimensions. Then, we study the bivariate copula in detail. Finally, we consider subfamilies of the new family of copulas that exhibit specific shapes of dependence.