Clustering dynamics in a class of normalised generalised gamma dependent priors (Q1695756)

Normalized generalized gamma processes induce nonparametric prior distributions widely used for mixture modelling in Bayesian statistics. In the paper under review, a class of dependent normalized generalized gamma priors induced by a stationary population model of Moran type is constructed. The asymptotic scaling for the dynamics of the number of clusters in the sample is studied, which in turn provides a dynamic measure of diversity in the underlying population. The limit is a positive non-stationary diffusion process, with unbounded drift and an entrance boundary at the origin. A new class of stationary positive diffusions is introduced, whose invariant measures are explicit and have power law tails, which approximate weakly the scaling limit.