Finite Mixtures of Skewed Matrix Variate Distributions

TL;DR

This paper introduces finite mixtures of skewed matrix variate distributions for clustering, filling a gap in the literature by extending mixture models to skewed matrix data with an EM-based estimation method.

Contribution

It proposes a novel approach for clustering with skewed matrix variate distributions, including parameter estimation via an expectation-conditional maximization algorithm.

Findings

Effective clustering demonstrated on simulated data.

Application to real data shows practical utility.

Method outperforms traditional models in skewed data scenarios.

Abstract

Clustering is the process of finding underlying group structures in data. Although mixture model-based clustering is firmly established in the multivariate case, there is a relative paucity of work on matrix variate distributions and none for clustering with mixtures of skewed matrix variate distributions. Four finite mixtures of skewed matrix variate distributions are considered. Parameter estimation is carried out using an expectation-conditional maximization algorithm, and both simulated and real data are used for illustration.