A/B testing guides
Practical guides to help you design better experiments β from picking the right test to deciding when to stop.
How to choose the right statistical test
Not sure whether to use a z-test, t-test, chi-square, or something else? Walk through a decision tree based on your metric type to find the right approach.
Read guide βA/B test statistical significance explained
Learn what statistical significance really means, how p-values work, and why a 95% confidence level doesn't mean a 95% chance of being right.
Read guide βUnderstanding A/B test sample size
Learn what determines sample size, how baseline rates and effect sizes interact, and the most common mistakes that lead to underpowered tests.
Read guide βHow long should you run an A/B test?
Convert sample size into calendar days, account for traffic volume and allocation, and understand why running tests in full-week cycles matters.
Read guide βHow to analyze A/B test results
Step-by-step guide to analyzing A/B test results correctly: check significance, effect size, confidence intervals, and make the right decision.
Read guide βBayesian vs frequentist A/B testing
Compare the two main statistical frameworks for A/B testing. Learn when to use each approach and how they interpret results differently.
Read guide βCommon A/B testing mistakes
Avoid the most common A/B testing mistakes: peeking at results, underpowered tests, wrong metrics, and more.
Read guide βA/B testing for small traffic sites
How to run meaningful A/B tests with limited traffic. Strategies for small websites: bigger changes, Bayesian methods, and adjusted expectations.
Read guide β