Describing differences by discriminant analysis
Discriminant analysis is a statistical analysis dating back to Fisher (1936 - Linear Discriminant Analysis (LDA)), as we have already mentioned earlier. It is a method for describing, through a one-dimensional function, the difference between two or more groups and allocating each observation to the group of origin. This is a classification problem, where the groups are known a priori and one or more new observations are classified into one of the known groups based on the measured characteristics. Each observation must have a score on one or more quantitative predictor measures, and a score on a group measure. Discriminant analysis is useful in determining whether a set of variables is effective in predicting category membership.
In MATLAB, the discriminant analysis model is created on the following assumptions:
- Each class generates data using a multivariate normal distribution. That is, the model assumes that data generated has a Gaussian mixture...
