Regression residual plots
Draws the four standard checks of a linear regression: standardized residuals against standardized predicted values, a histogram and a normal P-P plot of the residuals, and studentized residuals against leverage (with Cook’s distance).
Menu: Graphs → More charts → Regression residual plots…
When should I use it?
- Checking linearity, equal variance, normal residuals and influential cases after a regression.
What are the assumptions?
- A fitted linear regression with numeric predictors.
How do I run it in StatLab?
- Choose the dependent variable and predictors.
How do I read the output?
| Output | Meaning |
|---|---|
| ZRESID vs ZPRED | Should be a shapeless cloud around 0; a funnel means unequal variance, a curve means non-linearity. |
| Leverage plot | Labelled cases have large influence (Cook’s D above 4/N). |
Worked example
On the practice survey dataset (File → Sample dataset), this command — which the dialog's Paste button also produces — runs the procedure:
PROC vizResiduals /y=score /vars=(age pre).
Computed by StatLab's validated procedure code when this page was built. The example only illustrates the steps; choose variables that fit your own research question.
What are common mistakes?
- Deleting influential cases without a substantive reason.