Finite Mixtures of Multivariate Skew Laplace Distributions

TL;DR

This paper introduces finite mixtures of multivariate skew Laplace distributions to effectively model skewness and heavy tails in heterogeneous data, utilizing EM algorithm for parameter estimation and demonstrating its performance through simulations and real data.

Contribution

The paper presents a novel mixture model combining skewness and heavy tails, with an EM-based estimation method, for better modeling of complex data distributions.

Findings

Effective modeling of skewness and heavy tails in data

EM algorithm successfully estimates model parameters

Model performs well in simulations and real data applications

Abstract

In this paper, we propose finite mixtures of multivariate skew Laplace distributions to model both skewness and heavy-tailedness in the heterogeneous data sets. The maximum likelihood estimators for the parameters of interest are obtained by using the EM algorithm. We give a small simulation study and a real data example to illustrate the performance of the proposed mixture model.