Funnel plot

Funnelplot.png

Graphical tool for detecting bias in meta-analyses

Template:Infobox plot

A funnel plot is a type of scatter plot used primarily in meta-analysis to check for the presence of publication bias or other types of bias. The plot is a simple graphical representation that helps to visualize the relationship between study size and effect size.

Structure

A funnel plot typically plots the effect size from individual studies on the horizontal axis against a measure of study size, such as the standard error or the sample size, on the vertical axis. The name "funnel plot" comes from the shape that is expected when there is no bias: the plot should resemble a symmetrical inverted funnel.

Interpretation

In the absence of bias, the plot should be symmetrical because smaller studies will scatter widely at the bottom of the graph, with the spread narrowing among larger studies at the top. If there is publication bias, the plot will often appear asymmetrical because studies with non-significant or unfavorable results are less likely to be published.

Applications

Funnel plots are widely used in systematic reviews and meta-analyses to assess the risk of bias. They are particularly useful in the field of medicine, where they help to ensure that the conclusions drawn from a meta-analysis are not unduly influenced by the selective publication of studies.

Limitations

While funnel plots are a useful tool, they are not without limitations. Asymmetry in a funnel plot can be caused by factors other than publication bias, such as true heterogeneity between study results, differences in study quality, or chance. Therefore, funnel plots should be interpreted with caution and in conjunction with other methods of bias detection.

See also

• Meta-analysis
• Publication bias
• Systematic review
• Effect size
• Standard error