Finite Mixture of Birnbaum–Saunders Distributions Using the k-Bumps Algorithm

Mixture models have received a great deal of attention in statistics due to the wide range applications found recent years. This paper discusses finite mixture model Birnbaum–Saunders distributions with G components, which is an important supplement that developed by Balakrishnan et al. (J Stat Plann Infer 141:2175–2190, 2011) who considered two components. Our proposal enables modeling proper multimodal scenarios greater flexibility for or more where partitional clustering method, named k-bumps, used as initialization strategy proposed EM algorithm maximum likelihood estimates parameters. Moreover, empirical information matrix derived analytically account standard error, and bootstrap procedures testing hypotheses about number components are implemented. Finally, we perform simulation studies evaluate results analyze real dataset illustrate usefulness method.