Forest plots are the signature figure of meta-analysis. This guide explains every element — squares, the diamond, confidence intervals, I², and the null line.
A forest plot displays the individual effect estimates from each study in a meta-analysis, alongside the pooled (combined) estimate. It allows readers to see both the direction and magnitude of each study's result.
The squares. Each square represents one study's point estimate. The size of the square is proportional to the study's statistical weight — larger squares come from larger, more precise studies.
The horizontal lines. The line through each square is the 95% confidence interval. A wider line means more uncertainty; a narrower line means more precision.
The vertical null line. For mean differences, the null line is at 0. For ratio measures (OR, RR, HR), it is at 1. Studies whose CI crosses the null line are not statistically significant at p < 0.05.
The diamond. The diamond at the bottom represents the pooled estimate. Its centre is the pooled effect; its width is the 95% confidence interval. A diamond that does not touch or cross the null line indicates a statistically significant pooled effect.
I² statistic. Values under 25% suggest low heterogeneity; 25–50% moderate; above 50% substantial; above 75% considerable.
The bottom of the plot shows "Favours control" and "Favours intervention" — indicating which side of the null line indicates benefit for each group.
All analytical features included in the free trial. No credit card, no installation, no R or Python.
Create free account