Free Sample Size Calculator
Find out how many survey responses you need for statistically valid results.
Recommended Sample Size
responses needed
(% of your population)
Population
Confidence Level
%
Margin of Error
±%
Z-Score
With this sample size, you can be % confident your results are accurate within ±%.
How to Use This Calculator
- Enter your population size — if you know the total number of people in your target group (e.g., 5,000 employees, 100,000 customers). Leave blank for general population surveys.
- Choose your confidence level — 95% is standard for most surveys
- Select your acceptable margin of error — ±5% is common for most research
- Click Calculate to see how many responses you need
Why Sample Size Matters
Sample size determines how reliable your survey results will be. Too few responses and your data might not represent the whole population. Too many and you're wasting time and resources.
A properly calculated sample size ensures your results are statistically valid — meaning you can trust that the patterns you see in your sample reflect what's true for the entire population.
The Formula
n = (Z² × p × (1-p)) / e²
With finite population correction applied when population size is known
Where:
- n = required sample size
- Z = z-score for your confidence level
- p = expected proportion (0.5 for maximum variability)
- e = margin of error (as decimal)
Quick Reference: Common Sample Sizes
| Population | ±3% error | ±5% error | ±10% error |
|---|---|---|---|
| 500 | 341 | 217 | 81 |
| 1,000 | 516 | 278 | 88 |
| 10,000 | 964 | 370 | 96 |
| 100,000 | 1,056 | 383 | 96 |
| 1,000,000+ | 1,066 | 384 | 97 |
*Based on 95% confidence level, 50/50 distribution
Ready to collect your survey responses?
Create beautiful surveys that people want to complete. Get the sample size you need. Try it yourself 👇
- 40% higher completion rates than regular forms
- Unlimited forms & responses — free forever
- No credit card required
Frequently Asked Questions
What confidence level should I use?
95% is the standard for most research and surveys. Use 99% for critical decisions where you need near-certainty. 90% is acceptable for preliminary research or when resources are limited.
What margin of error is acceptable?
±5% is standard for most surveys. For important business decisions, aim for ±3% or less. For quick pulse checks, ±10% can be acceptable. The smaller the margin, the more responses you'll need.
What if I don't know my population size?
Leave it blank. The calculator will use the formula for an infinite (or very large) population. This gives you a conservative estimate that works for any population over about 20,000.
Why does 50/50 give the largest sample size?
When your responses could split 50/50, there's maximum uncertainty in the data. This requires more responses to be confident in the results. If you know responses will be more skewed (like 80/20), you need fewer responses.
How do I account for non-response?
If you expect only 25% of people to respond, multiply your required sample size by 4. For example, if you need 400 responses and expect 25% response rate, send surveys to 1,600 people.
Related Free Tools
View all tools →
Legal
🔒 Data securely stored with AWS in EU 🇪🇺