Compare independent correlations
Compare two independent Pearson correlations on the Fisher z scale.
Your entries stay in this page’s memory and are not submitted to us. Downloads are generated locally. Reloading or leaving the page clears your entries. Do not enter patient information.
Use correlations strictly inside −1 to 1 and whole sample sizes ≥4. Samples must be independent; overlapping or paired correlations are unsupported.
The starting values are hypothetical. Results update as you edit. Use aggregate or synthetic inputs only.
Calculation results
- Fisher z-scale contrast
- 0.49041463
- Contrast SE
- 0.19702907
- Test z
- 2.489047
- Approximate two-sided p
- 0.012808602
How to interpret the output
The contrast uses atanh(r1)−atanh(r2) with SE sqrt(1/(n1−3)+1/(n2−3)). A normal approximation assumes independent approximately bivariate-normal samples. It tests a correlation difference on the transformed scale; it is not a confidence interval for the raw difference.
Method referenceSource checked 2026-11-06. Read the reproducible calculator validation report.