CRO & Experimentation
A/B Test Sample Size Calculator
How many visitors before your test is conclusive.
Calculate the required sample size per variant to detect a minimum effect at 95% confidence and 80% power. Prevents calling tests early.
Inputs
Adjust to model your scenario
3.5%
%
10%
%
A 10% relative lift on a 3.5% baseline = 3.85%.
80%
%
Visitors needed per variant
45,373
To detect a relative lift of 10% on a 3.5% baseline at 95% confidence, you need 45,373 visitors per variant. Plan your test runtime accordingly.
Total visitors (control + variant)
90,746
Formula
n ≈ (z₍α/2₎ + z_β)² × (p₁(1−p₁) + p₂(1−p₂)) ÷ (p₂ − p₁)²
FAQ
How operators use this calculator.
For mature funnels, 5–10%. For early tests where any signal helps, 15–25%.
Related tools
Tools operators run alongside this one.
Need more than the math?
Get the SAZ team running this for your business.
Email info@Sedighi.ca or call (604) 632-4959. A senior partner responds within one business day.
Responding to inquiries within 1 business day