Profile of the group i, also called the barycenter of the group, is a vector P i :
and in the case of standardized data, it becomes
where is the mean of the variable xv for the cases belonging to the group i and Sv is the overall standard deviation of this variable.
Moreover, the program provides a possibility of using "weighted" distance, called Displacement, which is defined as follows:
The program starts using an initial classification variable defined a priori, or a random sample of cases or a stepwise sample of cases, which constitute the initial core of the groups. An iterative procedure refines the results by stabilizing the cores. The final group constitutes the categories of the classification variable. The number of typology groups may be reduced using an algorithm of hierarchical ascending classification