Sample Size Calculator
Choose your confidence level and margin of error to see how many responses your survey needs.
How it is calculated
The basic formula is n = z² × p(1 − p) ÷ e², where z comes from the confidence level (1.96 for 95%), p is the expected proportion and e is the margin of error. With 95% confidence, ±5% margin and p = 50%, you need 385 responses. For a smaller population, the finite population correction n ÷ (1 + (n − 1) ÷ N) lowers the number. For example, a school of 600 students needs about 235.
Choosing the inputs
- Confidence level: 95% is standard for research and theses. 99% needs many more responses.
- Margin of error: ±5% is common. Halving it to ±2.5% needs about four times as many responses.
- Proportion: leave it at 50% if you don't know. That gives the safest (largest) sample.
Plan for people who don't reply: if you expect 20% to respond, send the survey to five times the sample size. The sample must also be random. A large but biased sample (only your friends, only one city) can still give wrong results.
How it works
- Enter — type or paste your values or text.
- Get the result — it is worked out in your browser.
- Adjust — change the inputs to compare, or copy the result.
Related tools
View allPrefer to just describe the task? The AI Assistant can convert, compress and resize files from a short instruction.
Rate this tool
Log in to leave a review.