Nonparametric Bayesian models through probit stick-breaking processes

Abstract

We describe a novel class of Bayesian nonparametric priors based on stick-breaking constructions where the weights of the process are constructed as probit transformations of normal random variables. We show that these priors are extremely exible, allowing us to generate a great variety of models while preserv-ing computational simplicity. Particular emphasis is placed on the construction of rich temporal and spatial processes, which are applied to two problems in nance and ecology. © 2011 International Society for Bayesian Analysis.