The Concept
This is one of the most famous examples used to illustrate the difference between correlation and causation in statistics.
The Data Pattern
| Month | Ice Cream Sales | Shark Attacks | Temperature |
|---|---|---|---|
| January | Low | Very Low | Cold |
| February | Low | Very Low | Cold |
| March | Medium | Low | Mild |
| April | Medium | Low | Mild |
| May | High | Medium | Warm |
| June | Very High | High | Hot |
| July | Very High | Very High | Hot |
| August | Very High | Very High | Hot |
| September | High | Medium | Warm |
| October | Medium | Low | Mild |
| November | Low | Very Low | Cold |
| December | Low | Very Low | Cold |
The Misleading Correlation
What the data shows: Strong positive correlation between ice cream sales and shark attacks
Wrong conclusion: “Ice cream causes shark attacks!” or “Shark attacks cause people to buy ice cream!”
The real explanation: Both are caused by a third variable – hot weather/summer season
Why This Happens
. Hot Weather Effects:
- More people buy ice cream
- More people go to beaches
- More people swim in the ocean
- Higher chance of shark encounters
. The Hidden Variable:
- Temperature/season is the true cause
- Creates a spurious correlation
- Classic example of confounding variables
Key Learning Points
✅ Correlation ≠ Causation
✅ Look for hidden variables
✅ Consider logical explanations
✅ Question apparent relationships
