ABSTRACT
The basic aim of all clustering methods is to assign objects to groups (clusters) according to similarities in their specific characteristics. Two objects assigned to the same cluster should share similar specified characteristics (variables, patterns, symbols, etc.), whereas two objects allocated to different clusters should be less similar. Objects might be cases of either a data matrix or variables. For example, countries (cases) might be classified in clusters according to their values in selected variables. Alternatively, variables might be clustered into groups, so that cluster 1 contains variable X1, X2, and X4, cluster 2 variables X3, X5, etc. In most applications, cases are clustered. Therefore, these two terms (objects, cases) will be used here synonymously.
