What is it about?
Much has been written about the need to identify all studies when performing a meta-analysis. The reverse problem is that of making sure that data are not counted twice. This paper discusses how and why this happens and highlights several related ways in which the evidence can be overstated.
Featured Image
Why is it important?
Warns the reader of a neglected problem in meta-analysis: there may be less evidence than is appears to be tha case.
Read the Original
This page is a summary of: Overstating the evidence – double counting in meta-analysis and related problems, BMC Medical Research Methodology, February 2009, Springer Science + Business Media,
DOI: 10.1186/1471-2288-9-10.
You can read the full text:
Resources
Guernsey sums it up
Guernsey McPearson recounts his experience of double counting in meta-analysis.
A note regarding Lee's checks for minimum numbers of subjects where relative risks have been calculated
Points out that there is a problem in applying Lee's checks (referred to in the BMC article) to relative risks
Contributors
The following have contributed to this page
