Multivariate asymmetric distributions on the unitary hypercube: Properties and applications

Abstract- In this talk, a family of multivariate asymmetric distributions over the unitary hypercube defined in terms of well-known symmetric elliptical distributions will be presented. Here, we aim to study fundamental properties, such as the characterization of the density function for some types of distributions, as well as other properties, such as identifiability loss, quantiles, conditional and marginal distributions, and moments. In addition, simulation studies were performed to verify the asymptotic behavior of the estimated parameter values. Finally, the developed model was employed on real data, where, using convenient metrics, the degree of goodness-of-fit of the model to the real data was verified.