Model Fit (Intuition) Math Example 2

Follow the full solution, then compare it with the other examples linked below.

Example 2

medium
Residual plot for a linear model shows a clear U-shaped pattern. What does this indicate about the model, and what should be done?

Solution

  1. 1
    A U-shaped residual pattern means: residuals are negative at small and large x-values, positive at middle x-values
  2. 2
    This indicates: the true relationship is curved (non-linear), but a straight line was fitted
  3. 3
    Consequence: the linear model systematically underestimates at extremes and overestimates in the middle
  4. 4
    Fix: try a non-linear model (quadratic, polynomial, or transformation of variables)

Answer

U-shaped residuals indicate non-linearity — the linear model is misspecified; a curved model is needed.
Residual plots diagnose model assumptions. Random scatter → good fit. Patterns (U-shape, fan, cycles) → model violations. The U-shape specifically reveals that a non-linear relationship was incorrectly modeled as linear.

About Model Fit (Intuition)

Model fit describes how closely a statistical model's predictions match the observed data — measured by residuals, R2R^2, or loss functions.

Learn more about Model Fit (Intuition) →

More Model Fit (Intuition) Examples

Example 1 easy

A scatter plot of weight vs. height shows points loosely scattered around a line. Two measures of fi

Example 3 easy

Three models have [formula] values: Model A = 0.95, Model B = 0.50, Model C = 0.10. Rank them by goo

Example 4 hard

A model has [formula] in-sample but shows a fanning residual plot (residuals grow larger as [formula

← All Model Fit (Intuition) Examples Model Fit (Intuition) Concept