Product & Analytics / Experimentation
Statistical Significance (Experimentation) ~ (p-value; stat-sig; "significant at 95%")
A rule for deciding whether an A/B test result is real signal rather than noise.
The fork, why two teams get different numbers
Three methodologies give different verdicts on the same data.
In the Metric Library
- The full fork, both definitions worked all the way through
- The trap that makes the number lie, on a real export
- Every formula variant, spelled out
- The reconciliation anchor, what to tie it to and when to refuse
Reference: Neyman-Pearson / NHST convention; sequential-testing literature (Wald SPRT · alpha-spending / Lan-DeMets); Bayesian A/B-testing convention