Sample Size to Compare Two Proportions (WHO Lwanga-Lemeshow)
Sample size per group to compare two proportions, by a hypothesis test or by the precision of their difference.
Open the calculator → Runs in your browser. Data leaves only if you deliberately send a problem report from the interactive tool.
Example
- Hypothesis test or estimate of the difference
- Test whether the two proportions differ
- First group
- 5 %
- Second group
- 15 %
- Significance level
- 5 %
- Power
- 90 %
- One- or two-sided test
- One-sided
Result: 153 per group, 306 in all: to detect 5% against 15% with a one-sided test at 5% significance and 90% power.
The tool opens with these values already filled in. Replace them with your own.
What you enter
- Hypothesis test or estimate of the difference
- First group: anticipated proportion
- Second group: anticipated proportion
- Significance level (test mode)
- Power (test mode)
- One- or two-sided test (test mode)
- Confidence level (difference mode, %)
- Absolute precision of the difference in percentage points (difference mode)
- Design effect (optional; blank is 1, simple random sampling)
How this is calculated
Citation
Lwanga SK, Lemeshow S. Sample size determination in health studies: a practical manual. World Health Organization, Geneva, 1991 (ISBN 92 4 154405 8): Tables 4 (difference with absolute precision) and 5 (hypothesis test, pooled under the null, unpooled under the alternative), Examples 9 to 12. Read the source ↗
A reference and educational tool. Not medical, legal, or financial advice, and not a substitute for clinician judgment.