Finite sample Bernstein-von Mises theorem for semiparametric problems
From MaRDI portal
Abstract: The classical parametric and semiparametric Bernstein -- von Mises (BvM) results are reconsidered in a non-classical setup allowing finite samples and model misspecification. In the case of a finite dimensional nuisance parameter we obtain an upper bound on the error of Gaussian approximation of the posterior distribution for the target parameter which is explicit in the dimension of the nuisance and target parameters. This helps to identify the so called emph{critical dimension} of the full parameter for which the BvM result is applicable. In the important i.i.d. case, we show that the condition " is small" is sufficient for BvM result to be valid under general assumptions on the model. We also provide an example of a model with the phase transition effect: the statement of the BvM theorem fails when the dimension approaches . The results are extended to the case of infinite dimensional parameters with the nuisance parameter from a Sobolev class. In particular we show near normality of the posterior if the smoothness parameter exceeds 3/2.
Recommendations
- Critical dimension in the semiparametric Bernstein-von Mises theorem
- Nonasymptotic approach to Bayesian semiparametric inference
- The semiparametric Bernstein-von Mises theorem
- A Bernstein-von Mises theorem for smooth functionals in semiparametric models
- Semiparametric Bernstein-von Mises theorem and bias, illustrated with Gaussian process priors
Cites work
- A Bernstein-von Mises theorem for discrete probability distributions
- A Bernstein-von Mises theorem in the nonparametric right-censoring model
- A high-dimensional Wilks phenomenon
- A semiparametric Bernstein-von Mises theorem for Gaussian process priors
- An analysis of Bayesian inference for nonparametric regression
- An MCMC approach to classical estimation.
- Asymptotic normality of posterior distributions for exponential families when the number of parameters tends to infinity.
- Asymptotic normality of posterior distributions in high-dimensional linear models
- Asymptotic Normality of Semiparametric and Nonparametric Posterior Distributions
- Asymptotic Statistics
- Asymptotics in statistics: some basic concepts
- Bernstein-von Mises theorem for linear functionals of the density
- Bernstein-von Mises theorems for Gaussian regression with increasing number of regressors
- Consistency of objective Bayes factors as the model dimension grows
- General frequentist properties of the posterior profile distribution
- scientific article; zbMATH DE number 3733065 (Why is no real title available?)
- scientific article; zbMATH DE number 47310 (Why is no real title available?)
- Misspecification in infinite-dimensional Bayesian statistics
- Nonparametric Bernstein-von Mises theorems in Gaussian white noise
- On Bayes procedures
- On the Bernstein-von Mises phenomenon in the Gaussian white noise model
- On the Bernstein-von Mises theorem with infinite-dimensional parameters
- Parametric estimation. Finite sample theory
- Propagation-separation approach for local likelihood estimation
- The Bernstein-von Mises theorem and nonregular models
- The Bernstein-von Mises theorem for the proportional hazard model
- The Bernstein-von Mises theorem under misspecification
- The consistency of posterior distributions in nonparametric problems
- The semiparametric Bernstein-von Mises theorem
Cited in
(29)- On the Bernstein-von Mises theorem with infinite-dimensional parameters
- Selection of KL neighbourhood in robust Bayesian inference
- Robust Bayes-like estimation: rho-Bayes estimation
- Adaptive Bayesian inference for current status data on a grid
- Bayesian high-dimensional semi-parametric inference beyond sub-Gaussian errors
- Continuous forcing spectrum of regular hexagonal polyhexes
- Nonparametric Bayesian analysis of the compound Poisson prior for support boundary recovery
- On frequentist coverage errors of Bayesian credible sets in moderately high dimensions
- Large ball probabilities, Gaussian comparison and anti-concentration
- Bayesian regression with nonparametric heteroskedasticity
- Nonasymptotic approach to Bayesian semiparametric inference
- Accelerated meta-algorithm for convex optimization problems
- Additive Bayesian variable selection under censoring and misspecification
- The semiparametric Bernstein-von Mises theorem
- Critical dimension in the semiparametric Bernstein-von Mises theorem
- Asymptotic normality, concentration, and coverage of generalized posteriors
- Construction of credible intervals for nonlinear regression models with unknown error distributions
- Frequentist consistency of variational Bayes
- Bernstein-von Mises theorem and misspecified models: a review
- On accuracy of Gaussian approximation in Bayesian semiparametric problems
- On proximity of distributions of successive sums with respect to the Prokhorov distance
- Frequentist guarantees of distributed (non)-Bayesian inference
- Improved dimension dependence in the Bernstein-von Mises theorem via a new Laplace approximation bound
- Generalized median of means principle for Bayesian inference
- Accuracy of Gaussian approximation for high-dimensional posterior distributions
- Skewed Bernstein-von Mises theorem and skew-modal approximations
- Matching prior pairs connecting maximum a posteriori estimation and posterior expectation
- Skew-symmetric approximations of posterior distributions
- A Bernstein-von Mises theorem for smooth functionals in semiparametric models
This page was built for publication: Finite sample Bernstein-von Mises theorem for semiparametric problems
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q273627)
