Explore the evidence
Environment 02 · Prediction decision lab
One point can tilt the conclusion
An advertising team is relating campaign spending to sales. Move one unusual campaign and observe correlation, regression, and residuals together.
FrameExploreInterpretDecide
Interpret
What does r miss?
Move the point or switch to a curved pattern.
Decide
Would you use the line?
Decide whether this fitted line is suitable for predicting a campaign beyond the observed spending range. Consider shape, unusual points, and extrapolation.
See the mathematics and assumptions
Correlation measures the strength and direction of linear association. The least-squares line minimizes the sum of squared residuals. Neither establishes causation, and extrapolation beyond observed data can be unreliable.