Trying to be precise about vagueness

Stephen Senn*

*Corresponding author for this work

Research output: Contribution to journalArticleResearchpeer-review

86 Citations (Scopus)

Abstract

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 of prior distribution is tentatively proposed. Finally, some practical recommendations are made that stress the value both of fixed effect analyses and of frequentist approaches as well as various diagnostic investigations.

Original languageEnglish
Pages (from-to)1417-1430
Number of pages14
JournalStatistics in Medicine
Volume26
Issue number7
DOIs
Publication statusPublished - 30 Mar 2007
Externally publishedYes

Keywords

  • Bayesian methods
  • Fixed effects
  • Graphical representation
  • HGLM
  • Meta-analysis
  • Profile likelihood
  • Random effects

Fingerprint

Dive into the research topics of 'Trying to be precise about vagueness'. Together they form a unique fingerprint.

Cite this