Meta-Analysis Calculator

Use this meta-analysis calculator to combine effect estimates from several independent studies. Each spreadsheet row represents one study. Select the input format, assign the appropriate columns, and numiqo converts every study to a common effect estimate and sampling variance before pooling the results.

Supported meta-analysis inputs

• Binary outcomes: events and totals for two groups, analyzed as an odds ratio, risk ratio, or risk difference.
• Continuous outcomes: sample size, mean, and standard deviation for two groups, analyzed as Hedges' g or a mean difference.
• Generic effects: an already calculated effect estimate and its standard error.
• Correlations: a correlation coefficient and sample size, pooled on the Fisher z scale.

How to calculate a meta-analysis

1. Paste one study per row into the data table.
2. Select the appropriate input format and effect measure.
3. Assign one spreadsheet column to each required role.
4. Optionally select a study-label column so study names appear in the results and forest plot.

The results include fixed-effect and DerSimonian-Laird random-effects estimates, study weights, 95% confidence intervals, Cochran's Q, I², tau², a forest plot, a funnel plot, and Egger's regression test for funnel asymmetry.

Interpreting the results

The fixed-effect model assumes that all studies estimate one common true effect. The random-effects model allows the true effect to vary between studies. I² describes how much of the observed variability is attributable to heterogeneity rather than sampling error. A funnel plot or a significant Egger intercept can indicate asymmetry, but it cannot by itself establish publication bias. Egger's test should be interpreted cautiously when fewer than ten studies are available.