Bernstein-von Mises theorem for the Pitman-Yor process of nonnegative type

Bernstein-von Mises theorem for the Pitman-Yor process of nonnegative type

Franssen, S.E.M.P. (TU Delft Statistics)
van der Vaart, A.W. (TU Delft Statistics)

2022

The Pitman-Yor process is a random probability distribution, that can be used as a prior distribution in a nonparametric Bayesian analy-sis. The process is of species sampling type and generates discrete distribu-tions, which yield of the order n^σ different values (“species”) in a random sample of size n, ifthetypeσ is positive. Thus this type parameter can be set to target true distributions of various levels of discreteness, making the Pitman-Yor process an interesting prior in this case. It was previously shown that the resulting posterior distribution is consistent if and only if the true distribution of the data is discrete. In this paper we derive the dis-tributional limit of the posterior distribution, in the form of a (corrected) Bernstein-von Mises theorem, which previously was known only in the con-tinuous, inconsistent case. It turns out that the Pitman-Yor posterior distribution has good behaviour if the true distribution of the data is discrete with atoms that decrease not too slowly. Credible sets derived from the posterior distribution provide valid frequentist confidence sets in this case. For a general discrete distribution, the posterior distribution, although con-sistent, may contain a bias which does not converge to zero at the^√n rate and invalidates posterior inference. We propose a bias correction that solves this problem. We also consider the effect of estimating the type parameter from the data, both by empirical Bayes and full Bayes methods. In a small simulation study we illustrate that without bias correction the coverage of credible sets can be arbitrarily low, also for some discrete distributions.

Bernstein-von Mises theo-rem
credible set
empirical Bayes
Pitman-Yor process
species sampling
weak convergence

http://resolver.tudelft.nl/uuid:6ffecad6-4a1a-4295-98db-9a12b346921a

https://doi.org/10.1214/22-EJS2077

1935-7524

Electronic Journal of Statistics, 16 (2), 5779-5811

Institutional Repository

journal article

© 2022 S.E.M.P. Franssen, A.W. van der Vaart