Studies // Cited work
Bias in meta-analysis detected by a simple, graphical test
Egger, M., Davey Smith, G., Schneider, M., & Minder, C. (1997). Bias in meta-analysis detected by a simple, graphical test.
Level D Cross-sectional study doi:10.1136/bmj.315.7109.629
What this study supports
Supports the claims that funnel-plot asymmetry was associated with meta-analyses later contradicted by large trials and was present in a sizeable minority of published meta-analyses. Asymmetry is consistent with publication bias but has other possible causes, and the medical sample may not represent psychology.
- Who was studied
- Eight pairs of meta-analyses and large trials, plus funnel plots from 37 journal meta-analyses and 38 Cochrane reviews.
- Design
- Cross-sectional study
- Level of evidence
- Cross-sectional, observational, qualitative work and narrative reviews.
Claims that rest on it
No claim in the ledger rests on this work yet.