10.8 - Summary

In this lesson we learned:

  • How to determine which type of discriminant analysis is appropriate, linear or quadratic;
  • How the linear discriminant function is used to classify a subject into the appropriate population;
  • About issues to consider when selecting prior probabilities that a randomly selected subject belongs to a particular population;
  • How to use posterior probabilities to assess the uncertainty of the classification of a particular subject;
  • How to use cross-validation and confusion tables to assess the efficacy of discriminant analysis.