IBM Support

Quadratic discriminant analysis in SPSS

Technote (troubleshooting)


The results of Box's M test from a discriminant analysis indicate that the assumption of the equality of covariance matrices is not supported. I understand that quadratic discriminant analysis does not require this assumption. Can I perform a quadratic discriminant analysis in SPSS?

Resolving the problem

Quadratic discriminant analysis is not available using SPSS. However, you can choose to classify cases based upon separate covariance matrices (as opposed to the default use of the pooled covariance matrix). Using separate covariance matrices is one way to get around the problem of inequality of covariance matrices. When the number of predictors does not exceed the number of groups minus 1, the results of classifying cases using separate covariance matrices are identical to the results from quadratic discriminant analysis.

Related information

Need more help? Our Statistics forum is Live!

Historical Number


Document information

More support for: SPSS Statistics

Software version: Not Applicable

Operating system(s): Platform Independent

Reference #: 1479748

Modified date: 07 September 2016

Translate this page: