What is Simpson's paradox?
hardAnswer
- A trend that appears in several subgroups can reverse when the groups are combined.
- Classic example: a treatment looks better in each subgroup but worse overall, because group sizes and baseline rates vary.
- It's a warning to always inspect subgroup patterns and think causally — the right decomposition depends on the confounding structure, not on which cut looks prettier.
Check yourself — multiple choice
- It says group-level trends never differ from population trends
- A trend can reverse when data is aggregated across subgroups
- It only occurs with normally distributed data
- Simpson's paradox proves correlation implies causation
Aggregation over subgroups can flip a trend — always check by group.
#causal-inference
Practise Statistics Fundamentals
215 interview questions in this topic.
Related questions
- Why doesn't correlation imply causation?
- Users who adopt feature X churn less. Can you say the feature reduces churn?
- Potential outcomes framework — Rubin causal model.
- What is SUTVA?
- How do you handle confounders in observational studies?
- An aggregate trend reverses once you stratify. Which conditioning set is correct?