Biometrical Letters Vol. 50(1), 2013, pp. 1-14
|
SELECTION OF VARIABLES IN DISCRETE DISCRIMINANT ANALYSIS
Anabela Marques1, Ana Sousa Ferreira2, Margarida G.M.S. Cardoso3 1Barreiro College of Technology, Setúbal Polytechnic, IPS, Portugal, e-mail:anabela.marques@estbarreiro.ips.pt 2LEAD, Faculty of Psychology, University of Lisbon, Portugal, CEAUL and UNIDE, e-mail:asferreira@fp.ul.pt 3Dep. of Quantitative Methods of ISCTE - Lisbon University Institute, Portugal and UNIDE, e-mail:margarida.cardoso@iscte.pt |
In Discrete Discriminant Analysis one often has to deal with dimensionality problems. In fact, even a moderate number of explanatory variables leads to an enormous number of possible states (outcomes) when compared to the number of objects under study, as occurs particularly in the social sciences, humanities and health-related fields. As a consequence, classification or discriminant models may exhibit poor performance due to the large number of parameters to be estimated. In the present paper, we discuss variable selection techniques which aim to address the issue of dimensionality. We specifically perform classification using a combined model approach. In this setting, variable selection is particularly pertinent, enabling the handling of degrees of freedom and reducing computational cost.
combining models, Discrete Discriminant Analysis, variable selection
