Trying to be precise about vagueness

  title={Trying to be precise about vagueness},
  author={Stephen J Senn},
  journal={Statistics in Medicine},
  • S. Senn
  • Published 30 March 2007
  • Mathematics, Environmental Science, Psychology
  • Statistics in Medicine
A previous investigation by Lambert et al., which used computer simulation to examine the influence of choice of prior distribution on inferences from Bayesian random effects meta‐analysis, is critically examined from a number of viewpoints. The practical example used is shown to be problematic. The various prior distributions are shown to be unreasonable in terms of what they imply about the joint distribution of the overall treatment effect and the random effects variance. An alternative form… 

An informed reference prior for between‐study heterogeneity in meta‐analyses of binary outcomes

The distribution of between-study variance in published meta-analyses is described, and some realistic, informed priors for use in meta-Analyses of binary outcomes are proposed to improve the calibration of inferences from Bayesian meta-analysis.

You May Believe You Are a Bayesian But You Are Probably Wrong

An elementary sketch of some issues in statistical inference and in particular of the central role of likelihood is given. This is followed by brief outlines of what George Barnard considered were

A default prior for regression coefficients

It is argued that the uniform prior is not suitable as a default prior for inference about a regression coefficient in the context of the bio-medical and social sciences and proposed that a more suitable default choice is the normal distribution with mean zero and standard deviation equal to the standard error of the M-estimator.

Addressing the estimation of standard errors in fixed effects meta‐analysis

The impact of using estimated standard errors in fixed effects meta‐analysis is elucidated, showing why it does not go away in large samples and quantifying how badly miscalibrated standard inference will be if it is ignored.

The Choice of a Noninformative Prior on Between-Study Variance Strongly Affects Predictions of Future Treatment Effect

In this sample of Bayesian meta-analyses with binary outcomes, the choice of noninformative prior for between-study variance affected model fit and the predictions of future treatment effect.

A Note Concerning a Selection “Paradox” of Dawid's

This article briefly reviews a selection “paradox” of Dawid's, whereby Bayesian inference appears to be unchanged whether or not treatments have been selected for inspection on the basis of extreme

New methods for meta-analysis under a fixed effects framework, with frequentist and Bayesian estimation.

This dissertation proposes and develops methods for an alternative approach to meta-analysis, based on the assumption that the effects estimated in the different studies are unknown, but fixed and not necessarily identical, and proposed loss function takes into account the precision of the effect estimates.

Bayesian Random-Effects Meta-Analysis Using the bayesmeta R Package

  • C. Rover
  • Biology, Computer Science
    Journal of Statistical Software
  • 2020
The underlying theory of Bayesian meta-analyses, which allows for flexible prior specification and instant access to the resulting posterior distributions, is introduced and its usage is showcased.

Bayesian Random-Effects Meta-Analysis Using the bayesmeta R Package

The underlying theory of Bayesian meta-analyses, which allows for flexible prior specification and instant access to the resulting posterior distributions, is introduced and its usage is showcased.

Bayesian bivariate meta-analysis of correlated effects: Impact of the prior distributions on the between-study correlation, borrowing of strength, and joint inferences

Two key recommendations are identified to improve the robustness of multivariate meta-analysis results: the routine use of a Uniform(−1,1) prior distribution for ρB should be avoided and a sensible prior distribution should be identified, for example, by restricting values to be positive or negative as indicated by prior knowledge.



How vague is vague? A simulation study of the impact of the use of vague prior distributions in MCMC using WinBUGS

This chapter discusses the development of computer intensive simulation based methods such as Markov chain Monte Carlo (MCMC), increases in computing power and the introduction of powerful software such as WinBUGS that enabled increasingly complex models to be fitted.

A Bayesian Significance Test for Multinomial Distributions

SUMMARY A Bayesian significance test for multinomial distributions is discussed, together with the results of 18 numerical experiments in which the test is compared with non-Bayesian methods. Several

A likelihood approach to meta-analysis with random effects.

It is concluded that likelihood based methods are preferred to the standard method in undertaking random effects meta-analysis when the value of sigma B2 has an important effect on the overall estimated treatment effect.

Bayesian Statistics: An Introduction

This new fourth edition of Peter Lees book looks at recent techniques such as variational methods, Bayesian importance sampling, approximate Bayesian computation and Reversible Jump Markov Chain Monte Carlo, providing a concise account of the way in which the Bayesian approach to statistics develops as well as how it contrasts with the conventional approach.

Sampling-Based Approaches to Calculating Marginal Densities

Abstract Stochastic substitution, the Gibbs sampler, and the sampling-importance-resampling algorithm can be viewed as three alternative sampling- (or Monte Carlo-) based approaches to the

Hierarchical Generalized Linear Models

We consider hierarchical generalized linear models which allow extra error components in the linear predictors of generalized linear models. The distribution of these components is not restricted to

Systematic Review: Why sources of heterogeneity in meta-analysis should be investigated

This paper distinguishes between the concepts of clinical and statistical heterogeneity and exemplifies the importance of investigating heterogeneity by using published meta-analyses of epidemiological studies of serum cholesterol concentration and clinical trials of its reduction.

Applying Bayesian ideas in drug development and clinical trials.

A variety of tools for assessing the current evidence for treatment efficacy are presented, making use of graphical display to provide insight into ethical and efficiency issues in starting and stopping trials.

Controversies concerning randomization and additivity in clinical trials

  • S. Senn
  • Mathematics
    Statistics in medicine
  • 2004
Two controversies involving Fisher in the 1930s are discussed: one with Neyman concerning additivity and the other with Student concerning randomization.

Meta-analysis in clinical trials.