Outliers and Their Impact

Outliers are data points that behave very differently from the rest. They may come from sensor noise, operator error, or real process anomalies.

Why outliers matter:

• They pull the regression line in the wrong direction
• They reduce R²
• They distort variable importance (coefficient values)
• They create misleading predictions

How the system handles them:

• Automatically detects extreme Z-score values
• Flags rows with warnings in the interface
• Shows anomaly count in the prediction tab

Outliers are not always bad — sometimes they reveal real process issues worth investigating.