Sample Size Calculator

A higher confidence level or a smaller margin of error requires more responses. A 50% distribution gives the largest, safest sample when you cannot estimate the split in advance.

n₀ = z² × p(1−p) ÷ e², where z is the confidence z-score, p the response distribution and e the margin of error. For a finite population N, n = n₀ ÷ (1 + (n₀−1) ÷ N).

At 95% confidence (z = 1.96) with a 5% margin and 50% distribution, you need about 385 responses for a large population, or about 370 if the population is 10,000.

1. Pick your confidence level and margin of error.
2. Optionally enter your total population size.
3. Read off the number of completed responses you need.

• Confusing the number of completed responses with the number of invitations — adjust for your response rate.
• Using a tiny margin of error and being surprised by a huge sample.

The Sample Size Calculator tells you how many responses a survey needs to be statistically reliable for your chosen confidence level and margin of error, with an optional correction when your total population is small.

Researchers, students, marketers and product teams planning a survey or experiment.

• Get the exact number of responses to aim for.
• Choose your confidence level and margin of error.
• Finite-population correction for smaller groups.
• Private and instant — no sign-up.

• Planning a customer-satisfaction survey.
• Sizing an A/B test audience.
• Checking a study has enough participants.