Statistics
Sample size calculator
Estimate how many survey responses you need based on confidence level, margin of error, expected proportion, and population size.
Recommended sample
370
No population correction
385
Critical Z-value
1.95996
Interpretation
Under the above assumptions, a sample of approximately 370 observations would allow you to estimate a proportion with the selected margin of error and confidence level.
The formula assumes simple random sampling and is intended to estimate proportions. An actual survey may need adjustments for stratification, clustering, nonresponse, or design effects.
Frequently asked questions
What ratio should I use if I do not know it?
50% is a common conservative choice because it produces the greatest variability and usually requires a larger sample.
What does population 0 mean?
The tool interprets 0 as a very large population and does not apply finite population correction.
Why doesn't a much larger population require a much larger sample?
When estimating proportions, the margin of error depends mainly on the confidence level, variability, and sample size. The finite population correction has less influence when N is large.