Higher accuracy for Bayesian and frequentist inference: large sample theory for small sample likelihood

DOI10.1214/07-STS240zbMATH Open1246.62027arXiv0801.3751MaRDI QIDQ449760FDOQ449760

Authors: Augustine Wong, M. Bédard, D. A. S. Fraser 

Publication date: 1 September 2012

Published in: Statistical Science (Search for Journal in Brave)

Abstract: Recent likelihood theory produces $p$-values that have remarkable accuracy and wide applicability. The calculations use familiar tools such as maximum likelihood values (MLEs), observed information and parameter rescaling. The usual evaluation of such $p$-values is by simulations, and such simulations do verify that the global distribution of the $p$-values is uniform(0, 1), to high accuracy in repeated sampling. The derivation of the $p$-values, however, asserts a stronger statement, that they have a uniform(0, 1) distribution conditionally, given identified precision information provided by the data. We take a simple regression example that involves exact precision information and use large sample techniques to extract highly accurate information as to the statistical position of the data point with respect to the parameter: specifically, we examine various $p$-values and Bayesian posterior survivor $s$-values for validity. With observed data we numerically evaluate the various $p$-values and $s$-values, and we also record the related general formulas. We then assess the numerical values for accuracy using Markov chain Monte Carlo (McMC) methods. We also propose some third-order likelihood-based procedures for obtaining means and variances of Bayesian posterior distributions, again followed by McMC assessment. Finally we propose some adaptive McMC methods to improve the simulation acceptance rates. All these methods are based on asymptotic analysis that derives from the effect of additional data. And the methods use simple calculations based on familiar maximizing values and related informations. The example illustrates the general formulas and the ease of calculations, while the McMC assessments demonstrate the numerical validity of the $p$-values as percentage position of a data point. The example, however, is very simple and transparent, and thus gives little indication that in a wide generality of models the formulas do accurately separate information for almost any parameter of interest, and then do give accurate $p$-value determinations from that information. As illustration an enigmatic problem in the literature is discussed and simulations are recorded; various examples in the literature are cited.

Full work available at URL: https://arxiv.org/abs/0801.3751

Recommendations

• Accurate parametric inference for small samples
• Regression Analysis, Nonlinear or Nonnormal: Simple and Accurate p Values From Likelihood Analysis
• Stability and uniqueness of \(p\)-values for likelihood-based inference
• Three enigmatic examples and inference from likelihood
• Asymptotics and the theory of inference

zbMATH Keywords

asymptoticslikelihoodMetropolis-Hastings algorithm\(p\)-valuehigher orderthird orderBayesian posterior s-valuecanonical parameterdefault priormaximum likelihood departureregression example

Mathematics Subject Classification ID

Asymptotic properties of parametric estimators (62F12) Bayesian inference (62F15) Numerical analysis or methods applied to Markov chains (65C40) Probabilistic models, generic numerical methods in probability and statistics (65C20)

Cites Work

• Interval estimation for a binomial proportion. (With comments and a rejoinder).
• Title not available (Why is that?)
• Monte Carlo sampling methods using Markov chains and their applications
• Title not available (Why is that?)
• Modified signed log likelihood ratio
• Saddlepoint Approximations in Statistics
• An invariant form for the prior probability in estimation problems
• Ancillaries and conditional inference (with comments and rejoinder)
• Some Problems Connected with Statistical Inference
• Saddle point approximation for the distribution of the sum of independent random variables
• The roles of conditioning in inference. With comments and rejoinder
• Strong matching of frequentist and Bayesian parametric inference
• The Behrens-Fisher problem revisited: a Bayes-frequentist synthesis
• Title not available (Why is that?)
• A simple general formula for tail probabilities for frequentist and Bayesian inference
• Regression Analysis, Nonlinear or Nonnormal: Simple and Accurate p Values From Likelihood Analysis
• An essay towards solving a problem in the doctrine of chances. By the late Rev. Mr. Bayes, F. R. S. communicated by Mr. Price, in a letter to John Canton, A. M. F. R. S.
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Likelihood centered asymptotic model exponential and location model versions
• Computation of distribution functions from likelihood information near observed data
• Improved Likelihood Inference for Discrete Data
• Title not available (Why is that?)
• Approximations of marginal tail probabilities for a class of smooth functions with applications to Bayesian and conditional inference
• Title not available (Why is that?)
• Higher-Order Asymptotic Approximation: Laplace, Saddlepoint, and Related Methods
• Title not available (Why is that?)
• Title not available (Why is that?)

Cited In (7)

• Three enigmatic examples and inference from likelihood
• Higher order accurate procedures to compare two normal populations
• Is Bayes posterior just quick and dirty confidence?
• Objective Bayes models for compatibility assessment and bias estimation
• Confidence regions for comparison of two normal samples
• On default priors and approximate location models
• Improvement over bayes prediction in small samples in the presence of model uncertainty

This page was built for publication: Higher accuracy for Bayesian and frequentist inference: large sample theory for small sample likelihood

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q449760)