illusory-correlation-positive-positive-cell
IN premise — summaries/2026/08/24/wiki-Confirmation_bias-chunk-4.md
Created 2026-08-25T02:58:46+00:00
Illusory correlation is driven by over-weighting the positive-positive cell (both events present) and neglecting the other three cells of a 2×2 contingency table, as demonstrated in the arthritis-weather study where actual correlation was approximately zero.
Summary
People see fake connections between two things because they latch onto the times both events happened together and ignore the much larger set of cases where one or both did not. This is a structural blind spot in how we judge evidence, which is why claims like "rainy weather triggers arthritis pain" feel convincing to everyone even when the data shows essentially no link at all.