Yule–Simpson effect

Metadata

• Slug: 00492-yule-simpson-effect
• Type: PARADOX
• Tags: probability, statistics, causality
• Sources: 1

Axioms

• Assume the rules of the domain apply uniformly.
• Assume the observer’s criteria remain fixed.
• Assume classification boundaries stay consistent.
• Assume the model describes the real case.
• Assume repeated steps do not change the outcome.
• Assume no hidden variables are introduced midstream.

Contradictions

• Two reasonable lines of inference yield opposite conclusions
• A global rule conflicts with a local judgment
• A stable resolution appears to violate a starting premise
• Changing the framing reverses the outcome
• Intuition and formalism diverge at the same step

Prompts

• Which assumption is doing the most hidden work?
• What changes if you relax the smallest constraint?
• Does the paradox dissolve or relocate when reframed?
• What is conserved, and what is sacrificed?

Notes

Sources

• https://en.wikipedia.org/wiki/Yule%E2%80%93Simpson_effect

Overview

Simpson’s paradox is a phenomenon in probability and statistics in which a trend appears in several groups of data but disappears or reverses when the groups are combined. This result is often encountered in social-science and medical-science statistics, and is particularly problematic when frequency data are unduly given causal interpretations.

Tension

• Two reasonable lines of inference yield opposite conclusions.
• A global rule conflicts with a local judgment.
• A stable resolution appears to violate a starting premise.
• Changing the framing reverses the outcome.
• Intuition and formalism diverge at the same step.

Why It Matters

This entry tests how a stable rule-set can yield unstable conclusions under certain assumptions.

Prompts

• Which assumption is doing the most hidden work?
• What changes if you relax the smallest constraint?
• Does the paradox dissolve or relocate when reframed?
• What is conserved, and what is sacrificed?