A/B Test Sample Size Calculator
Your data never leaves your browserCalculate the required sample size per variation for a statistically valid A/B test.
Brie — Bug Reporting Tool
Found a bug while testing?
Brie captures screenshots, console logs, network data, and session replays in one click — so developers get the full context without the back-and-forth.
About A/B Test Sample Size Calculator
Enter your baseline conversion rate, the minimum detectable effect you want to measure, your desired confidence level, and statistical power. The calculator applies standard power analysis formulas to determine how many visitors each variation needs before you can trust the results. Running a test with too few samples leads to false positives or missed improvements — this tool removes the guesswork.
How to use
- Enter your current baseline conversion rate as a percentage (e.g. 5 for 5%).
- Set the minimum detectable effect — the smallest relative improvement worth detecting (e.g. 20 means a 20% lift over baseline).
- Choose a confidence level and statistical power, then read the required sample size per variation.
More Product Manager Tools
TAM SAM SOM Calculator
Calculate your Total Addressable Market, Serviceable Addressable Market, and Serviceable Obtainable Market.
Feature Prioritization Scorecard
Score and rank features by user value, business value, effort, and risk to find your highest-priority work.
OKR Formatter
Transform raw OKR text into a clean, structured document ready to share with your team.
Frequently Asked Questions
FAQs about A/B Test Sample Size Calculator
What is the minimum detectable effect?
The MDE is the smallest relative change in conversion rate you want to be able to detect. For example, an MDE of 20% on a 5% baseline means you want to detect a change to 6% (a 1 percentage-point lift). A smaller MDE requires a larger sample size.
What confidence level should I use?
Most product teams use 95%, which means there is a 5% chance of a false positive. For high-stakes decisions use 99%. For early-stage exploratory tests, 90% can be acceptable.
What is statistical power?
Power is the probability of detecting a real effect when one exists. 80% is the industry standard, meaning you accept a 20% chance of missing a real improvement. Higher power (e.g. 90%) requires larger sample sizes.
Does the calculator account for multiple variations?
The calculated sample size is per variation. For an A/B test with two buckets multiply by 2; for A/B/C multiply by 3. Running many simultaneous variations increases the risk of false positives.
How do I estimate test duration?
Divide the required total sample size by your average daily traffic to the tested page. For example, 10,000 visitors needed ÷ 500 daily visitors = 20 days minimum runtime.