On central limit theorems for Ewens-Pitman model

TL;DR

This paper proves a quenched functional central limit theorem for the total number of components in Chinese restaurant process-induced partitions, revealing the independence of sampling fluctuations and frequency fluctuations.

Contribution

It provides a new CLT for component counts in Ewens-Pitman models, strengthening recent results with a different approach and detailed fluctuation analysis.

Findings

Fluctuations split into sampling effect and frequency fluctuation parts.

Limit fluctuations are conditionally independent given the alpha-diversity.

Strengthens recent CLT results with a novel proof approach.

Abstract

We establish a quenched functional central limit theorem for the total number of components of random partitions induced by Chinese restaurant process with parameters $(\alpha,\theta), \alpha\in(0,1), \theta>-\alpha$. With $P_j$ denoting the asymptotic frequency of $j$-th table, it is well-known that the component count has the same law as the occupancy count of an infinite urn scheme with sampling frequencies being $(P_j)_{j\in\mathbb N}$. Our analysis follows this approach and is based on earlier results of Karlin (1967) and Durieu and Wang (2016). In words, our result reveals that the fluctuations of component count consist of two parts, one due to the sampling effect given the asymptotic frequencies $(P_j)_{j\in\mathbb N}$, the other due to the fluctuations of the random asymptotic frequencies, and in the limit the fluctuations of two parts are conditionally independent given the $\alpha$-diversity. Our result strengthens a recent central limit theorem obtained by Bercu and Favaro (2024) via a different method.