B0591
Title: Copulas.jl: Implementation of standard copula routines in Julia
Authors: Oskar Laverny - Aix-Marseille Université (France) [presenting]
Abstract: The "Copulas.jl" package is presented, a Julia package that brings standard dependence modelling tools and routines to this (rather new) computational language through native implementation. Copulas are distribution functions on the unit hypercube that are widely used (from theoretical probabilities and Bayesian statistics to applied finance or actuarial sciences) to model the dependence structure of random vectors apart from their marginals. Julia, on the other hand, is a trending programming language that leverages multiple dispatch concepts together with just ahead-of-time compilation to propose a very efficient programming environment for a lot of different tasks, including statistical estimation. This native implementation leverages the "Distributions.jl" framework and is therefore conveniently directly compatible with the broader ecosystem. Furthermore, the amount of code needed to obtain certain functionality is largely inferior to what was required for the competition, which ensures a much lower maintaining burden on one side, and a greater generality of the code on the other. Last, several subroutines, naively reimplemented, are clearly faster than the competition.