Parsimonious classification via generalised linear mixed models

Authors

G. Kauermann, University Bielefeld, Germany
J. T. Ormerod, University of New South WalesFollow
M. P. Wand, University of WollongongFollow

Publication Date

2008

Recommended Citation

Kauermann, G.; Ormerod, J. T.; and Wand, M. P., Parsimonious classification via generalised linear mixed models, Centre for Statistical and Survey Methodology, University of Wollongong, Working Paper 21-08, 2008, 15p.
https://ro.uow.edu.au/cssmwp/18

Abstract

We devise a classification algorithm based on generalised linear mixed model (GLMM) technology. The algorithm incorporates spline smoothing, additive model-type structures and model selection. For reasons of speed we employ the Laplace approximation, rather than Monte Carlo methods. Tests on real and simulated data show the algorithm to have good classification performance. Moreover, the resulting classifiers are generally interpretable and parsimonious.