A Comparison of Model-Based and Fuzzy Clustering Methods

Model-based and fuzzy clustering methods represent widely used approaches for soft clustering. In the former approach, it is assumed that the data are generated by a mixture of probability distributions where each component represents a different group or cluster. Each observation unit is ex-post assigned to a cluster using the so-called posterior probability of component membership. In the latter case, no probabilistic assumptions are made and each observation unit belongs to a cluster according to the so-called fuzzy membership degree. The aim of this work is to compare the performance of both approaches by means of a simulation study.