A/B test sample size calculator
Size your test before launch: traffic needed, duration in weeks and minimum detectable effect based on your conversion rate.
Calculation method
Pre-Test Calculator
Normal approximation of the difference between two proportions. Relative MDE = (zα + zβ) × √(2p(1−p)/n) / p, where p is the baseline conversion rate and n is the number of visitors per variant. zα is one-sided or two-sided depending on the setting, zβ corresponds to the target power (80% by default). Alpha is divided by the number of comparisons (Bonferroni correction).
Assumptions: independent visitors, balanced allocation between variants, stable conversion rate over the period, a single analysis with a sample size fixed in advance.
FAQ
Frequently asked questions about sizing an A/B test
- Sample size depends on four parameters: the baseline conversion rate, the minimum effect you want to detect (MDE), the confidence level and the statistical power. The calculator combines them using the normal approximation of the difference between two proportions and gives the number of visitors needed per variant, then the duration based on your traffic.
Tell us more about your project
We know how to increase the performance of your digital channels.
- Experimentation
- UX & Experience
- Personalization & CRM
- Data & Analytics
- Training
- Agentic commerce
