Results
Sample size needed
How it works
n = z² × p(1 − p) ÷ e²For a yes/no question, the number of responses you need depends on how precise you want to be (the margin of error e), how sure (the confidence level’s z) and the expected proportion p. Using 50% for p is the safe choice because it gives the largest sample. 95% confidence and ±5% needs 385 responses from a large population; a small population needs fewer, after the finite-population correction.
-
z² × p(1 − p) ÷ e²
1.959964² × 50% × (1 − 50%) ÷ 5%² = 384.15 -
Round up
384.15 → 385 -
Printed from rocketcalc.io/math/sample-size