Discriminant Analysis

The aim of discriminant analysis is to find a set of independent variables that predict membership of groups. It is a technique for classifying a set of observations into predefined categories. A prediction of a new observation to a category is then made possible.

Applying Discriminant Analysis, provide us with linear combinations of the original values. These new values give us the maximal separation between the groups of interest and are therefore better in showing us the differences across the groups of interest. Classification error rates can also be obtained to assess the performance of the derived discrimination functions.