A simple general formula for tail probabilities for frequentist and Bayesian inference

@article{Fraser1999ASG,
  title={A simple general formula for tail probabilities for frequentist and Bayesian inference},
  author={D. A. S. Fraser and Nancy Reid and J. Wu},
  journal={Biometrika},
  year={1999},
  volume={86},
  pages={249-264}
}
SUMMARY We describe a simple general formula for approximating the p-value for testing a scalar parameter in the presence of nuisance parameters. The formula covers both frequentist and Bayesian contexts and does not require explicit nuisance parameterisation. Implementation is discussed in terms of computer algebra packages. Examples are given and the relationship to Barndorff-Nielsen's approximation is discussed. 

Asymptotic likelihood inference

A simple general formula for approximating the p value for testing a scalar parameter in the presence of nuisance parameters is developed and a method for using this to approximate significance probabilities is described.

Exponential tilting in Bayesian asymptotics.

We use exponential tilting to obtain versions of asymptotic formulae for Bayesian computation that do not involve conditional maxima of the likelihood function, yielding a more stable computational

What a model with data says about theta

Recent likelihood theory gives complete inference for scalar parameters in continuous statistical models; the methodology involves conditioning at an initial stage, and marginalization at a

Frequentist and Bayesian Small-Sample Confidence Intervals for Gini’s Gamma Index in a Gaussian Bivariate Copula

This paper considers frequentist and Bayesian likelihood-based small-sample procedures to compute confidence intervals for Gini’s gamma index in the bivariate Gaussian copula model and straightforwardly extends to any measure of concordance which is available in closed form.

Accurate directional inference for vector parameters

We consider statistical inference for a vector-valued parameter of interest in a regular asymptotic model with a finite-dimensional nuisance parameter. We use highly accurate likelihood theory to

Comparison Between Bayesian and Frequentist Tail Probability Estimates

In this paper, we investigate the reasons that the Bayesian estimator of the tail probability is always higher than the frequentist estimator. Sufficient conditions for this phenomenon are

Default priors for Bayesian and frequentist inference

Summary.  We investigate the choice of default priors for use with likelihood for Bayesian and frequentist inference. Such a prior is a density or relative density that weights an observed likelihood

Strong matching of frequentist and Bayesian inferenceBY

SUMMARY We deene strong matching to be the equality of frequentist and Bayesian tail probabilities for the testing of scalar interest parameters; for the special case of a location model strong

Strong matching of frequentist and Bayesian inference

SUMMARY We deene strong matching to be the equality of frequentist and Bayesian tail probabilities for the testing of scalar interest parameters; for the special case of a location model strong

The Tangent Exponential Model

The likelihood function is central to both frequentist and Bayesian formulations of parametric statistical inference, and large-sample approximations to the sampling distributions of estimators and
...

References

SHOWING 1-10 OF 27 REFERENCES

Approximations of marginal tail probabilities and inference for scalar parameters

Two tail probability approximations of marginal tail probabilities are developed and numerical results given for conditional inference in location-scale and linear regression models show the approxIMations to be generally accurate even for small sample sizes.

Approximate Interval Probabilities

For models of parametric dimension 1 two parameterization invariant approximations to the conditional distribution function of the maximum likelihood estimator are considered. The first is derived by

Approximations of marginal tail probabilities for a class of smooth functions with applications to Bayesian and conditional inference

SUMMARY This paper presents an asymptotic approximation of marginal tail probabilities for a real-valued function of a random vector, where the function has continuous gradient that does not vanish

Likelihood and higher‐order approximations to tail areas: A review and annotated bibliography

Recent developments in higher-order asymptotic theory for statistical inference have emphasized the fundamental role of the likelihood function in providing accurate approximations to cumulative

Practical Use of Higher Order Asymptotics for Multiparameter Exponential Families

Recently developed asymptotics based on saddlepoint methods provide important practical methods for multiparameter exponential families, especially in generalized linear models. The aim here is to

An explicit large-deviation approximation to one-parameter tests

An approximation is derived for tests of one-dimensional hypotheses in a general regular parametric model, possibly with nuisance parameters. The test statistic is most conveniently represented as a

Conditional inference about a normal mean with known coefficient of variation

SUMMARY For a random sample from the normal distribution with known coefficient of variation, the minimal sufficient statistic includes an ancillary statistic. The effects of conditioning on the

Generalized Laplacian approximations in Bayesian inference

This paper presents a new Laplacian approximation to the posterior density of η = g(θ). It has a simpler analytical form than that described by Leonard et al. (1989). The approximation derived by

Simple Modifications for Signed Roots of Likelihood Ratio Statistics

SUMMARY In the context of inference about a scalar parameter in the presence of nuisance parameters, some simple modifications for the signed root of the log-likelihood ratio statistic R are

Confidence Intervals for a Normal Coefficient of Variation

Abstract This article presents an analysis of the small-sample distribution of a class of approximate pivotal quantities for a normal coefficient of variation that contains the approximations of