9 min read
Peeking in A/B testing: why "already significant" is not a result
Peeking in A/B testing inflates false positives. In 100,000 simulated A/A tests, daily checks turned a 5% error rate into 27.6%. What to do instead.
Articles about Statistical significance
RSS feedArticles for product managers and marketers about Statistical significance: plain explanations, examples and common mistakes.
9 min read
Confidence interval in A/B tests: what it really tells you
What a 95% confidence interval tells you in an A/B test, how to read one that crosses zero, and why it beats a bare p-value for ship decisions.
8 min read
P-value explained for product managers
P-value explained without jargon: what it tells you in an A/B test, what it doesn't, the most common misreadings and how to report results.