Abstract
Matrix-variate distributions can intuitively model the dependence structure of matrix-valued observations that arise in applications with multivariate time series, spatio-temporal, or repeated measures. This article develops an expectation-maximization algorithm for discriminant analysis and classification with matrix-variate t-distributions. The methodology shows promise on simulated datasets or when applied to the forensic matching of fractured surfaces or to the classification of functional magnetic resonance, satellite, or hand gestures images. Supplementary materials for this article are available online.
Acknowledgments
The authors thank the anonymous reviewer and the associate editor whose detailed comments and suggestions greatly improved the quality of this article.