Sample Size & Power Calculator
Estimate how many participants your study needs. Compare two proportions or two means, choose your significance level and power, and get the required sample size per group.
Two-sided test, no continuity correction. Add ~10–20% for expected dropout.
For education/research reference — verify against statistical software before publication. Computed locally.
What drives sample size
Four things determine how many participants you need: the effect size you want to detect (smaller effects need larger samples), the significance level (α), the desired power (1−β), and the variability of the outcome. This calculator handles the two most common designs — comparing two proportions or two means.
Frequently asked questions
How is sample size for two proportions calculated?+
n per group = (Z_α/2 + Z_β)² × [p₁(1−p₁) + p₂(1−p₂)] ÷ (p₁ − p₂)². This tool uses a two-sided test with the significance level and power you choose.
What significance level and power should I use?+
Convention is a two-sided α of 0.05 (95% confidence) and 80% power, though 90% power is common for confirmatory trials. Higher power and smaller effect sizes both increase the required sample size.
Should I add extra for dropouts?+
Yes. The result is the number needed with complete data. Inflate it for expected attrition — commonly by 10–20% — so the study stays adequately powered.
Is this suitable for publication?+
Use it for planning and teaching. For a protocol or manuscript, confirm with dedicated software (e.g. G*Power, PASS, R) and involve a statistician, especially for complex or survival designs.
Run your hospital on eMedHub
Cloud HIMS & EHR with built-in clinical tools, ABDM & NABH support.