Every regression model rests on assumptions. Learn to detect violations (non-linearity, heteroscedasticity, non-normal residuals, and influential outliers) using the four core diagnostic plots.
Sign in to track progress
Select Dataset
No violations detected. Residuals are random, variance is constant, and points follow the linear trend.
Plot 1: Residuals vs Fitted
Random scatter around zero: linearity assumption met.
Plot 2: Normal Q-Q
Points near the diagonal: residuals approximately normal.
Plot 3: Scale-Location
Horizontal band: constant variance (homoscedasticity) confirmed.
Plot 4: Leverage vs Residuals
Click highlighted points to remove them and see how the model changes.
Toggle flagged points to see how they affect the fitted model. Points with |standardized residual| > 2 or leverage > 4/n are flagged.
The Variance Inflation Factor (VIF) measures how much a predictor's variance is inflated due to correlation with other predictors. VIF > 10 suggests a predictor is nearly a linear combination of others.
| Variable | VIF | Status |
|---|---|---|
| Temperature | 1.04 | GOOD |
| Weekend flag | 1.03 | GOOD |
No meaningful correlation with other predictors.
Moderate correlation; monitor but usually acceptable.
High collinearity: standard errors are inflated.
Status for the currently selected dataset.
Residuals vs Fitted shows no systematic pattern
Scale-Location plot shows a horizontal band
Q-Q plot points lie near the diagonal
No points with high Cook's distance in leverage plot
Residuals vs Fitted
Random cloud around y=0
Curved or funnel-shaped pattern
Normal Q-Q
Points along the diagonal
S-curve or systematic departure
Scale-Location
Horizontal flat band
Rising or falling trend
Leverage / Cook's D
No points outside ±2 or high leverage
Points with Cook's D > 1 or h >> 4/n