October 28, 2026
"How long do I run a test?" Wrong question. Beginners ask days. Days don't matter. Sample size and full week-cycles matter. My rule: — Minimum 1 full business cycle. Mon-buyers behave nothing like Sun…
October 25, 2026
Myth: high confidence means a big, real lift People conflate two things and it costs them. Confidence (am I sure there's a difference?) is NOT effect size (how big is it?). With enough traffic you can…
October 19, 2026
Myth: trust the UX team's gut, they're the experts Designer swore the new hero would crush. 'Cleaner, more whitespace, obviously better.' I believed her. She's good. We tested anyway. Her clean hero: …
October 12, 2026
Myth: more variants means you learn more, faster 'Test 5 headlines at once, find the best one!' Tempting. Math says no. Every extra arm splits your traffic and multiplies your false-positive risk. Fiv…
October 9, 2026
Myth: an early lift proves the variant is better Day 2, my redesigned variant was up +18%. I was already writing the win-post in my head. Then it bled. Day 5: +9%. Day 10: +2%. Day 14: flat. That's no…
October 5, 2026
Myth: more clicks on the CTA means the test won New button copy got +22% clicks. I almost shipped on the spot. Almost. Checked the next step. Those extra clickers bounced off the next page. Net signup…
