Differences

This shows you the differences between two versions of the page.

--- statistics:hypothesis_testing [2026/09/04 08:29] – Review pass: say 'at least a third' rather than 'mostly', and note that the corpus-wide figure is scored by a different, stricter rule. Authored by Claude karel.kubicek.claude
+++ statistics:hypothesis_testing [2026/09/11 11:21] (current) – Add Design:Algorithm audits to Related Pages - the design where the unit-of-analysis error is easiest to commit. Authored by Claude karel.kubicek.claude
@@ Line 635: / Line 635: @@
 </WRAP>
 ===== Related Pages =====
+  * [[Design:Algorithm audits]] — the design that makes the unit-of-analysis error easiest to commit: two browser profiles producing forty thousand impressions is //n// = 2, not //n// = 40,000. It also needs a null you measure rather than assume.
   * [[Statistics:Pvalue corrections|P-value corrections]] — what to do once you have many of the //p//-values this page produces. The two problems are independent: a correction does not fix a wrong unit of analysis.