Evidence-appraisal glossary
Funnel plot
A funnel plot is a scatter graph used to check a meta-analysis for publication bias. Each study is a dot plotted by its effect size against its precision. Larger, more precise studies sit near the top; smaller ones scatter below. A roughly symmetric funnel shape is reassuring.
A funnel plot plots each study's effect estimate on the horizontal axis against a measure of its size or precision (often the standard error) on the vertical axis. Precise, large studies cluster near the top around the pooled estimate; smaller, less precise studies spread wider at the bottom, producing an inverted funnel. Symmetry suggests small and large studies agree. Asymmetry, such as a gap where small studies showing no effect or an unfavorable effect seem to be missing, can indicate publication bias, though it can also reflect true heterogeneity or study quality differences. When reading one, look at whether small studies are missing from one side and whether the authors ran a statistical test for asymmetry. For example, if every small trial in the funnel shows benefit and none show null results, the literature may be incomplete, and the pooled estimate could overstate the true effect. Funnel plots are unreliable with fewer than about ten studies.
This is a plain-language methodology definition for reading research. It is general education, not medical advice.