Overview for Discriminant Analysis

Use Discriminant Analysis to classify observations into two or more groups when you have a sample with known groups.

Using this analysis, you can do the following:

For example, a high school administrator uses discriminant analysis to determine which of three educational tracks a student should be placed in.

Where to find this analysis

To perform a discriminant analysis, choose Stat > Multivariate > Discriminant Analysis.

When the groups are initially unknown, use Cluster Observations or Cluster Variables.
If you have categorical predictors, or if you do not want to assume that the predictors are multivariate normal for each group, use logistic regression instead. If you have only two groups, use Fit Binary Logistic Model. If you have more than two groups, use Nominal Logistic Regression.