A re-evaluation of the 'quantile approximation method' for random effects meta-analysis

Dan Jackson*, Jack Bowden

*Corresponding author for this work

Research output: Contribution to journalArticle (Academic Journal)

25 Citations (Scopus)

Abstract

The quantile approximation method has recently been proposed as a simple method for deriving confidence intervals for the treatment effect in a random effects meta-analysis. Although easily implemented, the quantiles used to construct intervals are derived from a single simulation study. Here it is shown that altering the study parameters, and in particular introducing changes to the distribution of the within-study variances, can have a dramatic impact on the resulting quantiles. This is further illustrated analytically by examining the scenario where all trials are assumed to be the same size. A more cautious approach is therefore suggested, where the conventional standard normal quantile is used in the primary analysis, but where the use of alternative quantiles is also considered in a sensitivity analysis.

Original languageEnglish
Pages (from-to)338-348
Number of pages11
JournalStatistics in Medicine
Volume28
Issue number2
DOIs
Publication statusPublished - 30 Jan 2009

Keywords

  • Meta-analysis
  • Quantile approximation method
  • Random effects model

Fingerprint Dive into the research topics of 'A re-evaluation of the 'quantile approximation method' for random effects meta-analysis'. Together they form a unique fingerprint.

Cite this