The A/B Test Pre-Planning Calculator determines the required sample size and estimated test duration before running an experiment. It ensures tests have sufficient statistical power to detect meaningful effects. The formula is Sample Size = (Z-alpha + Z-beta)^2 x (p1(1-p1) + p2(1-p2)) / (p2-p1)^2. A good benchmark is to use 80% statistical power and 95% confidence as standard. PM Toolkit's free A/B test planning calculator helps product managers plan experiments with automatic duration estimation based on daily traffic and minimum detectable effect.
What is A/B Test Planning?
A/B test planning determines the sample size and duration needed before running an experiment. Proper planning prevents underpowered tests that waste time and overpowered tests that waste traffic.
Sample Size Formula
n = (Z_alpha + Z_beta)^2 x 2 x p(1-p) / MDE^2
Where: Z_alpha = z-score for significance level (1.96 for 95%), Z_beta = z-score for statistical power (0.84 for 80%), p = baseline conversion rate, MDE = minimum detectable effect
Test Duration Formula
Duration (days) = Required Sample Size / Daily Traffic per Variant
Planning Benchmarks
| Parameter | Standard | Conservative |
|---|---|---|
| Significance Level | 95% (alpha=0.05) | 99% (alpha=0.01) |
| Statistical Power | 80% | 90% |
| Minimum Test Duration | 1 week | 2 full business cycles |
Ask Claude, Cursor, or ChatGPT to run this calculator.
Install once. 23 web calculators · 17 in your AI · 12 PM workflows
You plan test 3% baseline · 10% MDE · 80% power
pmtk → n = 11,204 / variant · 18 days
A/B Test Sample Size Calculator
Plan sample size and duration before you launch. Underpowered tests waste time; overpowered tests waste traffic.
Updated
Auto-computed
%
%
Looking for: 5% → 5.75%
users/day
Quick Scenarios
Choose a preset configuration based on your needs
Not sure? Start with Standard for most A/B tests. Use Quick Test for rapid iterations, and High Confidence for changes affecting revenue or user experience.
Sample size per variant
13,534users
- Total
- 27,068
- Duration
- 28 days
- Target
- 5.75%
Test duration feasibility28 days
60d+42d21d1d
Slow — consider larger MDE to shorten timeline
Why this matters
Launching tests without power analysis is a coin flip dressed as data. Aim for MDE above 10% relative (practical significance), 95% confidence, 80% power, and plan for a 2× duration buffer around holidays and traffic dips.
This test might take 28 days. Consider increasing MDE to shorten the timeline.
Per variant
13,534
Users required
Total sample
27,068
Control + variant
Target conversion
5.75%
From 5%
Duration
28days
Long
Required Sample Size
ChallengingTotal Users Needed
27,068Control Group
13,534
Variant Group
13,534
Estimated Duration
28days
Per variant: 13,534 users
n = 2 × (Zα/2 + Zβ)² × p(1−p) ÷ MDE²
= n: 13,534 per variant · p: 5% · MDE: 15%
Two-proportion z-test. Higher confidence and power require larger samples.
Rate this calculator: