Rate of convergence of predictive distributions for dependent data
From MaRDI portal
Abstract: This paper deals with empirical processes of the type [C_n(B)=sqrt{n}{mu_n(B)-P(X_{n+1}in Bmid X_1,...,X_n)},] where is a sequence of random variables and the empirical measure. Conditions for to converge stably (in particular, in distribution) are given, where ranges over a suitable class of measurable sets. These conditions apply when is exchangeable or, more generally, conditionally identically distributed (in the sense of Berti et al. [Ann. Probab. 32 (2004) 2029--2052]). By such conditions, in some relevant situations, one obtains that or even that converges a.s. Results of this type are useful in Bayesian statistics.
Recommendations
- scientific article; zbMATH DE number 4056780
- Publication:4721403
- Convergence rate of conditional expectations
- Asymptotics of predictive distributions
- Rates of convergence for linear rank statistics with dependent data
- Rate of convergence of the density estimation of regression residual
- Convergencia del vector de probabilidad a posteriori bajo una distribucion predictiva
- On asymptotic properties of predictive distributions
Cites work
- scientific article; zbMATH DE number 5363669 (Why is no real title available?)
- scientific article; zbMATH DE number 3938277 (Why is no real title available?)
- scientific article; zbMATH DE number 3002711 (Why is no real title available?)
- scientific article; zbMATH DE number 3227597 (Why is no real title available?)
- scientific article; zbMATH DE number 2216954 (Why is no real title available?)
- scientific article; zbMATH DE number 3026923 (Why is no real title available?)
- A Strong Form of Stable Convergence
- A uniform limit theorem for predictive distributions
- Asymptotics in statistics: some basic concepts
- Bayesian nonparametrics
- Correction to: Universal prediction schemes
- Forward estimation for ergodic time series
- Improved Bounds for Equivalence of Bayes and Maximum Likelihood Estimation
- Limit theorems for a class of identically distributed random variables.
- Merging of Opinions with Increasing Information
- On almost sure convergence of conditional empirical distribution functions
- On the Bernstein-von Mises theorem with infinite-dimensional parameters
- Rate of convergence of predictive distributions for dependent data
- Universal schemes for prediction, gambling and portfolio selection
- Weak convergence and empirical processes. With applications to statistics
Cited in
(18)- On universal algorithms for classifying and predicting stationary processes
- Asymptotic behaviour of the empirical process for exchangeable data
- Central limit theorems for an Indian buffet model with random weights
- Uniform rates of the Glivenko-Cantelli convergence and their use in approximating Bayesian inferences
- Asymptotics of certain conditionally identically distributed sequences
- Exchangeability, predictive sufficiency and Bayesian bootstrap
- Convergencia del vector de probabilidad a posteriori bajo una distribucion predictiva
- Learning Theory
- Bayesian Predictive Inference Without a Prior
- A class of models for Bayesian predictive inference
- A central limit theorem and its applications to multicolor randomly reinforced urns
- Frequentistic approximations to Bayesian prevision of exchangeable random elements
- Rate of convergence of predictive distributions for dependent data
- Asymptotic predictive inference with exchangeable data
- The L2 Rate of Convergence for Event History Regression with Time‐dependent Covariates
- A uniform limit theorem for predictive distributions
- Rate of convergence of empirical measures for exchangeable sequences
- Asymptotics of predictive distributions
This page was built for publication: Rate of convergence of predictive distributions for dependent data
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q605900)