classres.getPerformance function

Calculation of classification performance parameters

Calculates and returns performance parameters for classification result (e.g. number of false negatives, false positives, sn, specificity, etc.).

classres.getPerformance(c.ref, c.pred)

Arguments

• c.ref: reference class values for objects (vector with numeric or text values)
• c.pred: predicted class values for objects (array nobj x ncomponents x nclasses)

Returns

Returns a list with following fields:

$fn	number of false negatives (nclasses x ncomponents)
$fp	number of false positives (nclasses x ncomponents)
$tp	number of true positives (nclasses x ncomponents)
$sensitivity	sn values (nclasses x ncomponents)
$specificity	specificity values (nclasses x ncomponents)
$specificity	ms ratio values (nclasses x ncomponents)

Details

The function is called automatically when a classification result with reference values is created, for example when applying a plsda or simca models.