The Fundamental Difference: Association vs Cause-and-Effect
What You'll Learn
You'll learn why finding that two variables move together doesn't mean one causes the other—a critical distinction for making sound decisions with data.
The Core Idea
Just because two things are correlated (they occur together or move in tandem) doesn't mean one causes the other. Correlation is about association: when X changes, Y tends to change too. Causation is about mechanism: changing X directly produces a change in Y.
You've learned to calculate Pearson's r, Spearman's rho, and Kendall's tau—all measures of correlation. These tell you how strongly two variables are related, but they never tell you why or which direction any influence flows.
Why This Matters
Consider a classic example: ice cream sales and drowning deaths are positively correlated. Does ice cream cause drowning? No! Both are caused by a third variable—hot summer weather. People swim more (increasing drowning risk) and buy more ice cream when it's hot.
Three common scenarios where correlation ≠ causation:
- Confounding variables: A hidden third factor causes both (like temperature above)
- Reverse causation: Maybe Y causes X, not X causes Y
- Pure coincidence: Random chance, especially with small samples or cherry-picked data
The Gold Standard
To establish causation, you typically need:
- Controlled experiments (randomized trials)
- Temporal precedence (cause comes before effect)
- A plausible mechanism
- Elimination of alternative explanations
Correlation analysis is exploratory—it raises questions but rarely answers them definitively.
Key Takeaway: Correlation measures association between variables; causation requires evidence that one variable directly produces changes in another. Never assume causation from correlation alone.