Bernstein - von Mises Theorem for growing parameter dimension

Abstract

This paper revisits the prominent Fisher, Wilks, and Bernstein -- von Mises (BvM) results from different viewpoints. Particular issues to address are: nonasymptotic framework with just one finite sample, possible model misspecification, and a large parameter dimension. In particular, in the case of an i.i.d. sample, the mentioned results can be stated for any smooth parametric family provided that the dimension \(p \) of the parameter space satisfies the condition "\(p^{2}/n \) is small" for the Fisher expansion, while the Wilks and the BvM results require "\(p^{3}/n \) is small".

References in corpus (1)

• Parametric estimation. Finite sample theory

Cited by in corpus (10)

• Frequentist Consistency of Variational Bayes
• Bootstrap confidence sets under model misspecification
• On the Bernstein-Von Mises Theorem for High Dimensional Nonlinear Bayesian Inverse Problems
• FarmTest: Factor-Adjusted Robust Multiple Testing with Approximate False Discovery Control
• Smoothed Quantile Regression with Large-Scale Inference
• Bayesian Graph Selection Consistency Under Model Misspecification
• A robust fusion-extraction procedure with summary statistics in the presence of biased sources
• Finite sample Bernstein-von Mises theorems for functionals and spectral projectors of the covariance matrix
• Non-Asymptotic Behavior of the Maximum Likelihood Estimate of a Discrete Distribution
• Robust Inference via Multiplier Bootstrap