Premium
Separation Failure in Linear Programming Discriminant Models
Author(s) -
Rubin Paul A.
Publication year - 1991
Publication title -
decision sciences
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.238
H-Index - 108
eISSN - 1540-5915
pISSN - 0011-7315
DOI - 10.1111/j.1540-5915.1991.tb01279.x
Subject(s) - linear discriminant analysis , discriminant , separation (statistics) , separable space , optimal discriminant analysis , discriminant function analysis , selection (genetic algorithm) , multiple discriminant analysis , function (biology) , artificial intelligence , mathematics , pattern recognition (psychology) , computer science , machine learning , mathematical analysis , evolutionary biology , biology
Linear programming discriminant analysis (LPDA) models are designed around a variety of objective functions, each representing a different measure of separation of the training samples by the resulting discriminant function. A separation failure is defined to be the selection of an “optimal” discriminant function which incompletely separates a pair of completely separable training samples. Occurrence of a separation failure suggests that the chosen discriminant function may have an unnecessarily low classification accuracy on the actual populations involved. In this paper, a number of the LPDA models proposed for the two‐group case are examined to learn which are subject to separation failure. It appears that separation failure in any model can be avoided by applying the model twice, reversing group designations.