A Unified Mathematical Programming Formulation for the Discriminant Problem

Stam, A. & Ragsdale, C.T. (1989). A Unified Mathematical Programming Formulation for the Discriminant Problem. IIASA Working Paper. IIASA, Laxenburg, Austria: WP-89-047

Preview

Text WP-89-047.pdf Download (457kB) | Preview

Abstract

In recent years, much research has been done on the application of mathematical programming (MP) techniques to the discriminant problem. While very promising results have been obtained, many of these techniques are plagued by a number of problems associated with the model formulation including unbounded, improper and unacceptable solutions as well as solution instability under linear transformation of the data. Some have attempted to prevent these problems by suggesting overly complex formulations which can be difficult to solve. Others have suggested formulations which solve certain problems but which create new ones. In this paper we develop a simple MP model which unifies many features of previous formulations and appears to avoid any solution problems. This approach also considers a classification gap often encountered in the related statistical techniques.

Actions (login required)

View Item