Title: Mixtures of common factor analyzers based on the restricted multivariate skew-t distribution
Authors: Tsung-I Lin - National Chung Hsing University (Taiwan) [presenting]
Wan-Lun Wang - Feng Chia University (Taiwan)
Mauricio Castro - Pontificia Universidad Catolica de Chile (Chile)
Abstract: Mixtures of common t factor analyzers (MCtFA) have been shown its effectiveness in robustifying mixtures of common factor analyzers (MCFA) when handling model-based clustering of the high-dimensional data with heavy tails. However, the MCtFA model may still suffer from a lack of robustness against observations whose distributions are highly asymmetric. A further robust extension of the MCFA and MCtFA models, called the mixture of common skew-t factor analyzers (MCstFA), is presented by assuming a restricted multivariate skew-t distribution for the common factors. The MCstFA model can be used to accommodate severely non-normal (skewed and leptokurtic) random phenomena while preserving its parsimony in factor-analytic representation and performing graphical visualization inlow-dimensional plots. A computationally feasible Expectation Conditional Maximization Either (ECME) algorithm is developed to carry out maximum likelihood estimation. The numbers of factors and mixture components are simultaneously determined based on common likelihood penalized criteria. The usefulness of the proposed model is illustrated with simulated and real datasets, and results signify its superiority over some existing competitors.