Experiments7 min read
How long should you run an A/B test?
Run an A/B test until it can detect the smallest lift worth acting on, in whole weeks. How to work it out, with a calculator for your own numbers.
Blog
Notes on testing, speed, and statistics.
What we learn building a website platform with A/B testing built in: how to run experiments that are fast for visitors and honest about results, with the numbers to back it up.
All posts
SEO7 min read
Does A/B testing hurt SEO? What Google says
Testing doesn't hurt SEO if you follow Google's four rules: don't cloak, use canonical links, use 302 redirects, and end tests on time. With a checklist.
Statistics8 min read
Why peeking at A/B tests finds false winners
Check a standard A/B test every day and its 5% false-positive rate quietly becomes 21%. We simulated 4,000 tests to show why, and what fixes it.
Performance8 min read
A/B test flicker: what causes it and how to fix it
Flicker is the flash of the original page visitors see before a testing script swaps in their variant. What causes it, what it costs, and how to remove it.
Run your first experiment this week. Build it, test it, ship the winner.
Start freeBook a demo
Free to start. No credit card required.