It sounds like you're asking about (Classification and Regression Trees) within Minitab , and possibly its integration with solid features (likely referring to solid data structures, stable model features, or solid decision rules).
These are often called in industrial statistics because they hold across shifts, batches, or operators. D. Solid model validation Using Minitab’s split-sample validation or k-fold cross-validation to ensure the tree doesn’t change much with new data. 3. How to Identify a "Solid Feature" in Minitab CART | Step | Action in Minitab | |------|-------------------| | 1 | Run CART® Regression or Classification | | 2 | In Validation , choose k-fold cross-validation (e.g., 10 folds) | | 3 | After fit, view Variable Importance chart | | 4 | Look for predictors with high importance AND small error bars | | 5 | Check Split History – solid features appear early and repeatedly | 4. Example (Hypothetical) Problem : Predict casting defect (yes/no) Predictors : Pour temp, Mold moisture, Alloy type, Cooling time
