Classification by Pairwise Coupling

We discuss a strategy for polychotomous classification that involves estimating class probabilities for each pair of classes, and then coupling the estimates together. The coupling model is similar to the Bradley-Terry method for paired comparisons. We study the nature of the class probability estimates that arise, and examine the performance of the procedure in real and simulated datasets. Classifiers used include linear discriminants, nearest neighbors, and the support vector machine. 1 Introduction We consider the discrimination problem with K classes and N training observations. The training observations consist of predictor measurements Department of Statistics, Sequoia Hall, Stanford University, Stanford California 94305; trevor@playfair.stanford.edu y Department of Preventive Medicine and Biostatistics, and Department of Statistics; tibs@utstat.toronto.edu x = (x 1 ; x 2 ; : : : x p ) on p predictors and the known class memberships. Our goal is to predict the class membe..