B0563
Title: Bayesian nonparametric modeling of latent partitions via Stirling-gamma priors
Authors: Alessandro Zito - Duke University (United States) [presenting]
Tommaso Rigon - University of Milano-Bicocca (Italy)
David Dunson - Duke University (United States)
Abstract: Dirichlet process mixtures are particularly sensitive to the value of the so-called precision parameter, which controls the behaviour of the underlying latent partition. Randomization of the precision through a prior distribution is a common solution, which leads to more robust inferential procedures. However, existing prior choices do not allow for transparent elicitation, due to the lack of analytical results. A novel prior is introduced and investigated for the Dirichlet process precision, the Stirling-gamma distribution. The distributional properties of the induced random partition are studied, with an emphasis on the number of clusters. Theoretical investigation clarifies the reasons for the improved robustness properties of the proposed prior. Moreover, under specific choices of its hyperparameters, the Stirling-gamma distribution is conjugate to the random partition of a Dirichlet process. With an ecological application, the usefulness of the approach for the detection of communities of ant workers is illustrated.
