RAGNU - A MICROCOMPUTER PACKAGE FOR 2-GROUP MATHEMATICAL PROGRAMMING-BASED NONPARAMETRIC CLASSIFICATION

In this manuscript, we introduce the PC-based software package RAGNU, a utility program that can be used, in conjunction with the LINDO opti mization software, for solving two-group classification problems using a class of recently developed nonparametric methods. The criteria use d to estimate the classification function are based on either minimizi ng a function of the absolute deviations from the surface that separat es the groups, or directly minimizing a function of the number of misc lassified observations. Since mathematical programming techniques are efficient tools for analyzing such problems, we will refer to this cla ss of nonparametric methods as MP-based methods. Recently, a number of research studies have reported that under certain data conditions MP- based methods can provide more accurate classification results than ex isting parametric statistical methods, such as Fisher's linear discrim inant function and logistic regression. It has also been shown that ex tensions of the MP-based formulations that incorporate non-linear (e.g ., quadratic) functions of the attribute values are a viable alternati ve to Smith's quadratic discriminant function. However, these robust M P-based classification methods have not yet been implemented in the ma jor statistical packages, and hence are beyond the reach of those stat istical analysts who are unfamiliar with mathematical programming tech niques. Currently, only those researchers who have written their own i nterface software programs are able to use MP-based classification met hods. Therefore, we believe that RAGNU contributes significantly to th e field of nonparametric classification analysis, in that it provides the research community with convenient access to this class of robust methods. RAGNU is available from the authors without charge.