Correlation is not causation

A scatter plot can show that two quantities tend to move together — that is called correlation. But correlation alone does not prove that one quantity causes the other.

A classic example

Ice-cream sales and the number of sunburns both rise in summer, so a scatter plot shows a positive association. But ice cream does not cause sunburn. A third factor — hot, sunny weather — drives both.

Why this matters

When you describe a scatter plot, you can say the two quantities are associated. Claiming one causes the other needs more than a graph — it needs an experiment or a clear explanation.

What you can say

• "There is a positive (or negative) association." — safe from a scatter plot.
• "One causes the other." — only with extra evidence.
• Watch for a hidden third factor that might explain both.

Three rules that always help

• A pattern shows association, not proof of cause.
• Look for a hidden factor that could drive both quantities.
• Describe the link; claim causes only with stronger evidence.

Keep going

• Practice: Identify the association
• Back to the scatter plots overview