Bayesian estimation of clustering structures in binned data

Binned data, a common type of data sets resulting from summarizing the original observations in a sequence of pairs of bins and frequencies, appear in different fields of research. There may exist different reasons to only provide this summary; however, the more important challenge is being able to perform statistical analyses based only on it. We present a Bayesian nonparametric model for clustering applicable to binned data. Clusters are modeled via random partitions, and within them a model-based approach is assumed. Inferences are performed by a Markov chain Monte Carlo method and the proposed method is evaluated using simulated and real data. Having particular interest in studying marine populations, we analyze samples of Lobatus (Strobus) gigas’ lengths, where the presence of up to three cohorts along the year was found, information useful for resource management.