Clustering right-skewed data stream via Birnbaum–Saunders mixture models: A flexible approach based on fuzzy clustering algorithm

Abstract

Despite the widespread use of Gaussian mixture model for clustering datasets, practical applications show that the skewed and leptokurtic mixture models can be considered as promising alternatives. This paper proposes a finite mixture of Birnbaum–Saunders (FM-BS) distributions for analyzing and clustering right-skewed, leptokurtic, and multimodal lifetime datasets. The maximum likelihood (ML) estimates of the proposed model are obtained by developing a computationally analytical expectation–maximization (EM) type algorithm, as well as a fuzzy classification maximum likelihood (FCML) type algorithm, that combines the advantages of fuzzy clustering and robust statistical estimators. Simulation studies demonstrate the accuracy and computational efficiency of the FCML algorithm to estimate parameters of the FM-BS distributions and to cluster samples drawn from the FM-BS distributions. Finally, some real datasets have been analyzed to illustrate how well the proposed FM-BS model estimates the membership values.