RESEARCH TOOLKIT · FREE

Sample size calculator

How many participants your study needs — for estimating a proportion or a mean, or comparing two groups. You get the working and a sentence ready for your Methods section.

What is your study trying to do?

Expected proportion%From a previous study. Unsure? 50% gives the largest, safest size.Precision (margin of error)%Absolute, e.g. 5 means ±5 percentage points.

Confidence

Expected non-response / drop-out%The size is increased to allow for it.Population size (optional)Only if small and known, e.g. all 600 nurses in a hospital.

SAMPLE SIZE

359

participants

Minimum 323, plus 10% for non-response.

Working

n = Z² × p × (1 − p) / d² = 1.96² × 0.3 × 0.7 / 0.05² = 322.69

Rounded up 323 ÷ (1 − 0.1) = 359

For your Methods section

Assuming an expected proportion of 30%, an absolute precision of 5% and 95% confidence, the minimum sample size was calculated as 323. Allowing for 10% non-response, 359 participants will be enrolled.

Free to use. Everything you enter stays in your browser; nothing is sent to us. Results are a guide — check them with your guide or statistician before you rely on them.

Not sure which values to use, or your design is more complex (matched, cluster, survival)? Our statisticians can work it out with you.

Get help with your protocol