Free Tool
A/B Test Sample Size Calculator
Calculate exactly how many visitors you need for statistically significant results. No guesswork, no signup required.
1 Enter Your Parameters
%
Your current conversion rate
%
Smallest improvement you want to detect (relative)
Advanced Settings
Common Mistakes to Avoid
- • Don't stop the test early when you see significance
- • Don't expect to detect tiny effects (5%) with small samples
- • Always run for at least 1-2 full weeks regardless of sample size
Pro Tips
- • Test bigger changes to detect effects with fewer visitors
- • Focus on high-traffic pages for faster results
- • Use 20-30% MDE as a realistic starting point
Sample Size Reference Table
Quick reference for common scenarios (95% confidence, 80% power, 2 variants)
| Baseline | 10% MDE | 20% MDE | 30% MDE | 50% MDE |
|---|---|---|---|---|
| 1% | 312,000 | 78,000 | 34,800 | 12,600 |
| 3% | 102,000 | 25,600 | 11,400 | 4,200 |
| 5% | 60,800 | 15,200 | 6,800 | 2,400 |
| 10% | 28,800 | 7,200 | 3,200 | 1,200 |
| 20% | 12,800 | 3,200 | 1,440 | 520 |