Sorry for what may be a silly question but I'm very new to pattern recognition and am having trouble understanding matlabs classify function.
I have a training set for which I have performed bartlett's test for equality of covariance matrices with equal numbers of cases for each class. This returns a p of 0 which I understand to mean I should use stratified covariance estimates for each group.
classify offers two options with stratified covariance
mahalanobis — Uses Mahalanobis distances with stratified covariance estimates
Quadratic — Fits multivariate normal densities with covariance estimates stratified by group
Assuming equal priors what is the difference between performing a discriminant analysis using the mahalanobis and quadratic options? for my data the quadratic seems to perform better but I would like to understand why.