Specialty › Precision & CI width

Difference between proportions

Precision-based sizing finds the per-group n that gives a confidence interval on a difference of proportions a target half-width.

What is Difference between proportions?

The Wald formula n = z² · (p₁·(1−p₁) + p₂·(1−p₂)) / E² uses the expected p values per arm. Conservatism via p = 0.5 in each arm; tighter values are available with Newcombe / Wilson formulations for unequal arms.

When should I use Difference between proportions?

Two-arm proportion-difference precision planning.

What data does it need?

p₁ + p₂ + target half-width + confidence.

What does it report?

Required n per group.

How do I interpret the result?

Use the most conservative (largest) n by setting p₁ = p₂ = 0.5 when uncertain about expected rates.