Example
Input: 5% Baseline, 20% MDE
Result: 10,000 Visitors/Var
Step-by-Step Guide
- Baseline: Current conversion rate (e.g. 5%).
- MDE: Minimum Detectable Effect (e.g. 20% uplift).
- Result: Visitors needed per variation.
What is A/B Test Sample Size Calculator?
Calculates the required sample size per variation to detect a specific improvement (Minimum Detectable Effect) with statistical confidence.
How it Works
Uses standard statistical formulas (power 80%, significance 95%) based on your baseline conversion rate and desired uplift.
FAQ
What is statistical significance?
The probability that the difference is not due to random chance (usually 95%).
What is MDE?
Minimum Detectable Effect - the smallest improvement you want to be able to measure.
Can I stop early?
No, 'peeking' creates bias. Run until the sample size is met.
One-tailed or Two-tailed?
This uses Two-tailed (standard) to detect both positive and negative changes.
Power?
Standard is 80% power (20% chance of missing a real effect).
Conclusion
Running a test without enough data leads to false positives. Use this calculator to ensure your A/B test runs long enough to provide valid, actionable data.