Premium
A Graph for Two Training Samples in a Discriminant Analysis
Author(s) -
Chang WeiChien
Publication year - 1987
Publication title -
journal of the royal statistical society: series c (applied statistics)
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.205
H-Index - 72
eISSN - 1467-9876
pISSN - 0035-9254
DOI - 10.2307/2347847
Subject(s) - linear discriminant analysis , graph , artificial intelligence , discriminant , pattern recognition (psychology) , training (meteorology) , computer science , mathematics , combinatorics , geography , meteorology
SUMMARY A graph which succinctly displays the separation between two training samples is presented. On one coordinate, the differences mainly due to the sample means are displayed; on the other coordinate, the separation solely due to the covariance matrices is shown. A straight line can be drawn to show the separation of the two samples on this graph. This contrasts with Sammon's graph in which both coordinates display the differences mainly due to the saple means. Artificial and real examples are provided to show that the proposed graph can be quite informative in the data analysis of the training samples.