DISCRIMINANT ANALYSIS

DISCRIMINANT ANALYSIS
It has been pointed our earlier, that the discriminant analysis is a useful tool for situations where the total sample is to be divided into two or more mutually exclusive and collectively exhaustive groups on the basis of a set of predictor variables. For example, a problem involving classifying sales people into successful and unsuccessful; classifying customers into owners or and non-owners of video tape recorder, are examples of discriminant analysis.
Objectives two group discriminant analysis:
1) Finding linear composites of the predictor variables that enable the analyst to separate the groups by maximizing among groups relative to with in-groups variation.
2) Establishing procedures for assigning new individuals, whose profiles but not group identity are known, to one of two groups.
3) Testing whether significant differences exist between the mean predictor variable profiles of the two groups.
4) Determining which variables account most for intergroup differences in mean profiles.