Correlation vs. Causation

Drag the correlation slider to regenerate the scatterplot so its data actually match r. Watch the line of best fit, then see why even a strong correlation does not prove cause.

Correlation ≠ causation.
r = 0.00
0.70

The third-variable problem

Try: set r = 0 (a random blob), then drag toward +1 and watch the points collapse onto the line. A tight line still does not mean one variable causes the other — a lurking third variable can produce the whole pattern.