Sample Size Calculator for Surveys
Calculate how many completed survey responses you need from confidence level, margin of error, population size, and planning assumptions.
Calculate completed survey responses
Start with the standard 95% confidence, ±5% margin of error, and conservative 50% proportion. Add population size when your audience is finite.
How certain you want to be in the estimate.
%
Use 5 for ±5%. Smaller margins need more responses.
Optional. Leave blank for unknown or very large populations.
%
Advanced. 50% is conservative when you are unsure.
%
Optional planning input for invitations needed.
385
For a large or unknown population, plan for at least 385 completed responses at 95% confidence and ±5% margin of error.
No finite population correction because population is blank.
Add a response rate to estimate survey invitations needed.
Common survey scenarios
| Confidence | Margin of error | Completed responses |
|---|---|---|
| 90% | ±5% | 271 |
| 95% | ±5% | 385 |
| 95% | ±3% | 1,068 |
| 99% | ±5% | 664 |
Formula and assumptions
This MVP calculator estimates sample size for survey proportions. For a large or unknown population it uses:
n0 = z² × p × (1 − p) / e²
When you enter a finite population size, it applies finite population correction:
n = n0 / (1 + (n0 − 1) / N)
- z
Z-score for the selected confidence level: 1.645 for 90%, 1.96 for 95%, and 2.576 for 99%.
- p
Expected proportion. Use 50% when you are unsure because it is the conservative maximum-variance assumption.
- e
Margin of error as a decimal. A ±5% margin is entered as 5.
- N
Finite population size. Blank means unknown or large population.
Example
A researcher surveying a broad customer audience with 95% confidence and ±5% margin of error should collect 385 completed responses. If the reachable population is 10,000 people, finite population correction lowers that to 370. At a 25% response rate, invite about 1,480 people.
Sample size FAQ
How many survey responses do I need?
For a large or unknown population, 95% confidence, ±5% margin of error, and a conservative 50% expected proportion, you need 385 completed responses.
What does population size mean?
Population size is the total audience you want to study. Leave it blank for a very large or unknown population, or enter a positive whole number to apply finite population correction.
Why is 50% expected proportion the default?
A 50% expected proportion is conservative because it produces the largest required sample size when you do not already know the likely result.
Does sample size fix survey bias?
No. Sample size addresses random sampling error only. It does not fix biased sampling, panel quality issues, screening errors, poor questionnaire design, or nonresponse bias.
Coming next
Planned calculators are listed without links until their pages exist.