Linkage is the method for determining how the proximity relationship between clusters is measured.

In Bayes decision theory, the classification problem is specified in terms of probabilities.

The posterior probability is the probability that an observation belongs to the m-th class.

Bayes’s classifier assigns an observation to the class with the largest posterior probability.

The ij-th element of the confusion matrix represents the number of observations of class i that the classifier says belongs to class j.