Simpson's Paradox Visualizer
Examine confounding variables dynamically. Toggle between global and clustered regression data to observe mathematical trends magically reverse polarity (Pearson r) when separated.
THE DANGER OF AGGREGATION
**Simpson's Paradox** occurs when a trend appears in several different groups of data but disappears or reverses when these groups are combined.
LURKING VARIABLES
The paradox is usually caused by a **lurking variable** (a third variable) that influences both of the variables being studied, distorting the overall relationship.
AP EXAM CONNECTION
Unit: Unit 2: Exploring Two-Variable Data (Topic 2.3)
Learning Objective: DAT-1.H
COMMON MISCONCEPTIONS
- Assuming a correlation in a total population applies to all subgroups.
KEY TAKEAWAYS
- Trends can reverse.
- Beware of lurking variables.
- Context matters in data.
PRACTICE QUESTIONS
Q1 (CONCEPTUAL): How can you resolve Simpson's Paradox?
Show Answer & Explanation
Answer: By looking at the disaggregated data.
Explanation: The true relationship is often clearer when you analyze the specific groups rather than the combined total.