Bayesian nonparametric mixture models represent a powerful statistical framework that extends traditional mixture modelling by allowing the number of mixture components to be inferred from the data ...

The Annals of Statistics, Vol. 48, No. 4 (August 2020), pp. 2277-2302 (26 pages) Motivated by problems in data clustering, we establish general conditions under which families of nonparametric mixture ...

Let τ be a prior distribution over the parameter space Θ for a given parametric model P θ, θ ∈ Θ. For the sample space X (over which P θ 's are probability measures) belonging to a general class of ...

Bayesian estimation and maximum likelihood methods represent two central paradigms in modern statistical inference. Bayesian estimation incorporates prior beliefs through Bayes’ theorem, updating ...