Title: Modelling multivariate skew and heavy-tailed data: A comparison of the main models
Authors: Sladjana Babic - Ghent University (Belgium) [presenting]
Christophe Ley - Ghent University (Belgium)
David Veredas - Vlerick Business School (Belgium)
Abstract: The most popular flexible classes of multivariate distributions are presented and their advantages and drawbacks are discussed. By flexible distribution we mean that, besides the usual location and scale parameters, the distribution has also both skewness and tail parameters. The following flexible families of multivariate distributions are presented: elliptical distributions, skew-elliptical distributions, multiple scaled mixtures of multinormal distributions, multivariate distributions based on the transformation approach, copula-based multivariate distributions and meta-elliptical distributions. A theoretical comparison based on the properties of each model is done, while we conduct a Monte Carlo simulation study to check the fitting abilities of every model. To this end we generate data from every model and compare the competitor models in terms of their fitting qualities. This allows us to draw general conclusions concerning the flexibility of the various distributions.