Hierarchical cluster analysis of groups of individuals : application to business data

3rd SMTDA Conference Proceedings, 11-14 June 2014, Lisbon Portugal.We present one example, in which the data are issued from a questionnaire in order to find satisfaction typologies (with the services provided by an automobile company) of independent groups of individuals. The Agglomerative Hierarchical Cluster Analysis (AHCA) was based on two approaches: one based on a particular case of the generalized weighted affinity coefficient, which deals with classical data, and the other one on the weighted generalized affinity coefficient for the case of symbolic/complex data. Both measures of comparison between elements were combined with classical and probabilistic aggregation criteria. We used the global statistics of levels (STAT) to evaluate the quality of the obtained partitions