Bernoulli
- Bernoulli
- Volume 25, Number 4A (2019), 2982-3015.
Uniform rates of the Glivenko–Cantelli convergence and their use in approximating Bayesian inferences
Emanuele Dolera and Eugenio Regazzini
Abstract
This paper deals with suitable quantifications in approximating a probability measure by an “empirical” random probability measure $\hat{\mathfrak{p}}_{n}$, depending on the first $n$ terms of a sequence $\{\tilde{\xi}_{i}\}_{i\geq1}$ of random elements. Section 2 studies the range of oscillation near zero of the Wasserstein distance $\mathrm{d}^{(p)}_{[\mathbb{S}]}$ between $\mathfrak{p}_{0}$ and $\hat{\mathfrak{p}}_{n}$, assuming the $\tilde{\xi}_{i}$’s i.i.d. from $\mathfrak{p}_{0}$. In Theorem 2.1 $\mathfrak{p}_{0}$ can be fixed in the space of all probability measures on $(\mathbb{R}^{d},\mathscr{B}(\mathbb{R}^{d}))$ and $\hat{\mathfrak{p}}_{n}$ coincides with the empirical measure $\tilde{\mathfrak{e}}_{n}:=\frac{1}{n}\sum_{i=1}^{n}\delta_{\tilde{\xi}_{i}}$. In Theorem 2.2 (Theorem 2.3, respectively), $\mathfrak{p}_{0}$ is a $d$-dimensional Gaussian distribution (an element of a distinguished statistical exponential family, respectively) and $\hat{\mathfrak{p}}_{n}$ is another $d$-dimensional Gaussian distribution with estimated mean and covariance matrix (another element of the same family with an estimated parameter, respectively). These new results improve on allied recent works by providing also uniform bounds with respect to $n$, meaning the finiteness of the $p$-moment of $\mathop{\mathrm{sup}}_{n\geq1}b_{n}\mathrm{d}^{(p)}_{[\mathbb{S}]}(\mathfrak{p}_{0},\hat{\mathfrak{p}}_{n})$ is proved for some diverging sequence $b_{n}$ of positive numbers. In Section 3, assuming the $\tilde{\xi}_{i}$’s exchangeable, one studies the range of oscillation near zero of the Wasserstein distance between the conditional distribution – also called posterior – of the directing measure of the sequence, given $\tilde{\xi}_{1},\ldots,\tilde{\xi}_{n}$, and the point mass at $\hat{\mathfrak{p}}_{n}$. Similarly, a bound for the approximation of predictive distributions is given. Finally, Theorems from 3.3 to 3.5 reconsider Theorems from 2.1 to 2.3, respectively, according to a Bayesian perspective.
Article information
Source
Bernoulli, Volume 25, Number 4A (2019), 2982-3015.
Dates
Received: December 2017
Revised: July 2018
First available in Project Euclid: 13 September 2019
Permanent link to this document
https://projecteuclid.org/euclid.bj/1568362049
Digital Object Identifier
doi:10.3150/18-BEJ1077
Mathematical Reviews number (MathSciNet)
MR4003571
Zentralblatt MATH identifier
07110118
Keywords
dominated ergodic theorem empirical measure exchangeability Glivenko–Cantelli theorem law of the iterated logarithm posterior distribution predictive distribution Wasserstein distance
Citation
Dolera, Emanuele; Regazzini, Eugenio. Uniform rates of the Glivenko–Cantelli convergence and their use in approximating Bayesian inferences. Bernoulli 25 (2019), no. 4A, 2982--3015. doi:10.3150/18-BEJ1077. https://projecteuclid.org/euclid.bj/1568362049
