A forest plot shows the effect size and confidence interval of each study in a meta-analysis, plus the pooled
result. It is the main figure of most systematic reviews.
Parts of a forest plot
One row per study: a square at the effect estimate and a horizontal line for its 95% CI.
Square size shows the study's weight in the analysis.
Diamond: the pooled estimate; its width is the pooled 95% CI.
Vertical line of no effect: at 1 for ratios (odds ratio, risk ratio, hazard ratio) and at 0
for differences (mean difference, standardised mean difference).
Use the right scale
Ratios should be plotted on a log scale so that 0.5 and 2 sit the same distance from 1. Differences use a
normal linear scale.
Data you need
For each study: name, effect estimate, lower CI and upper CI, and optionally the weight. Add the pooled values
and heterogeneity (I²) from your meta-analysis software.
Tips
Label which side favours treatment and which favours control.
Order studies by year or by effect size, and keep the order consistent with your tables.
Print the numbers in a column on the right if your journal prefers it.