Misclassification analysis of discriminant model

Abstract

This paper extends the criterion of the misclassification ratio of discriminant model and presents a new selection method of discriminant model. For selecting the discriminant model, this method establishes the rule of misclassification degree ratio through misclassification ratio of the discriminant model and misclassification degree of the samples. To test the effect of this method, this work uses seven UCI data sets. Numerical experiments on these examples indicate that this method has certain rationality and has a better effect to select a discriminant model.