Forest plot generator
Enter each study's effect and 95% confidence interval; Folio pools them — fixed-effect and random-effects, with I² heterogeneity — draws a publication-ready forest plot, and adds a funnel plot with Egger's test for publication bias. Download as SVG or PNG. Free, no sign-up; everything runs in your browser.
Enter each study’s effect estimate and 95% confidence interval. Standard errors are derived from the CIs; pooling uses inverse-variance weighting (fixed-effect and DerSimonian–Laird random-effects). Free — everything runs in your browser.
Writing the review?
Folio drafts with your own sources, checks every citation, and records a verifiable writing history — and pairs with our free PRISMA flow diagram generator.
What is a forest plot?
A forest plot is the signature figure of a meta-analysis. Each row is a study: a marker at its effect estimate, sized by how much weight it carries, with a horizontal line for its 95% confidence interval. A vertical reference line marks “no effect” (1 for ratios, 0 for differences). The diamond at the bottom is the pooled estimate across all studies — its centre is the summary effect and its width is the summary confidence interval.
This generator does the statistics for you: it derives each study's standard error from its confidence interval, weights studies by inverse variance, and pools them with both fixed-effect and DerSimonian–Laird random-effects models, reporting Q, I², and τ² so you can judge heterogeneity. It pairs with Folio's free PRISMA flow diagram generator — the two figures every systematic review and meta-analysis needs.
Frequently asked
Is this forest plot generator free?
Yes — completely free, with no sign-up. It runs entirely in your browser, so your data is never uploaded, and you can use the plot in any thesis, publication, or report.
How does it pool the studies?
It derives each study’s standard error from its 95% confidence interval, then pools using inverse-variance weighting — both fixed-effect and DerSimonian–Laird random-effects — and reports heterogeneity as Q, I², and τ². Ratio measures (OR, RR, HR) are pooled on the log scale.
What do I need to enter?
For each study: a label and its effect estimate with the lower and upper bounds of the 95% confidence interval. Choose whether the measure is a ratio (odds/risk/hazard ratio) or a difference (mean difference). That’s enough to weight, pool, and plot.
Can I download it for publication?
Yes — download a vector SVG (scales with no pixelation, ideal for journals) or a high-resolution PNG. Both are generated in your browser.
Which should I report, fixed or random effects?
Most meta-analyses report random-effects, which allows the true effect to vary across studies; fixed-effect assumes one common effect. Toggle between them to see both — the diamond, weights, and pooled estimate update accordingly.
Does it check for publication bias?
Yes. Switch to the Funnel plot tab to see each study charted against its standard error inside a pseudo-95% confidence funnel, plus Egger’s regression test for small-study effects (funnel asymmetry). Egger’s test needs at least three studies.