Find out how many responses you need before your survey results mean something — and how many people you'll need to invite to get them.
With 385 responses you can be 95% confident the true answer is within ±5% of what your survey shows.
Calculated in your browser — nothing you type is sent anywhere.
Population size is everyone you could survey: all your customers, members or staff. If it's very large or you don't know, leave it blank — above a few thousand it barely changes the answer.
Confidence level is how sure you want to be. 95% is the usual choice. Margin of error is how far the survey result might be from the true answer: 5% means a result of 60% really sits somewhere between 55% and 65%.
Add your expected response rate and the calculator tells you how many invitations to send. For email surveys to customers, 10–30% is typical; to your own staff it's usually higher.
The calculator uses Cochran's formula: n₀ = z² × p(1 − p) / e², where z is 1.645, 1.96 or 2.576 for 90%, 95% or 99% confidence, e is the margin of error, and p is 0.5 — the most cautious assumption when you don't know how people will answer.
For a known population N, it applies the finite population correction: n = n₀ / (1 + (n₀ − 1) / N). That's why a survey of 500 people needs far fewer than 500 answers, but never more than the population itself.
At 95% confidence and a 5% margin, a large population needs 385 responses; a population of 1,000 needs 278.
Forms that ask one question at a time get finished more often — and every completed answer counts towards your sample. Free for 1,000 responses a month.
Build your survey free