Resubstitution classification edge for discriminant analysis classifier
Estimate the Resubstitution Edge of Discriminant Analysis Classifiers
Estimate the quality of a discriminant analysis classifier for Fisher's iris data by resubstitution.
Load Fisher's iris data set.
Train a discriminant analysis classifier.
Mdl = fitcdiscr(meas,species);
Compute the resubstitution edge.
redge = resubEdge(Mdl)
redge = 0.9454
edge — Classification edge
Classification edge obtained by resubstituting the training data into the calculation of edge, returned as a scalar.
The edge is the weighted mean value of the classification margin. The weights are class prior probabilities. If you supply additional weights, those weights are normalized to sum to the prior probabilities in the respective classes, and are then used to compute the weighted average.
The classification margin is the difference between the classification score for the true class and maximal classification score for the false classes.
The classification margin is a column vector with the same number
of rows as in the matrix
X. A high value of margin
indicates a more reliable prediction than a low value.
For discriminant analysis, the score of a classification is the posterior probability of the classification. For the definition of posterior probability in discriminant analysis, see Posterior Probability.
Version HistoryIntroduced in R2011b
R2023b: Observations with missing predictor values are used in resubstitution and cross-validation computations
Starting in R2023b, the following classification model object functions use observations with missing predictor values as part of resubstitution ("resub") and cross-validation ("kfold") computations for classification edges, losses, margins, and predictions.
In previous releases, the software omitted observations with missing predictor values from the resubstitution and cross-validation computations.