SVM classification
Support-vector classifier with a holdout confusion matrix and, for two classes, an ROC.
When to use it
Use SVM classification when the outcome is a category and you want a holdout confusion matrix without trees. Random forest of the same problem is random forest classification.
Assumptions
The outcome is categorical. Features are numeric. Classes with fewer than two rows are dropped. Kernel, C, and class weights are not exposed. Holdout fraction 0.25; HTTP and chat dispatch both honour test_fraction.
Running it in Tensr
Options
Prop
Type
Reading the output
The same strong pass/fail sample and the same two features. Kernel and C are not user controls.
| Actual \ Predicted | 0 | 1 |
|---|---|---|
| 0 | 30 | 3 |
| 1 | 13 | 14 |
Train accuracy = 0.722, test accuracy = 0.733, n = 240. Hours was built to move the pass rate strongly, so holdout accuracy should sit clearly above chance.
Reporting (APA 7)
Holdout classification of passed from hours and anxiety, n = 240. Test accuracy = 0.733, train accuracy = 0.722.
Coming from SPSS
SPSS has no SVM dialog. Tensr’s item is on the ML menu, Classification → Support Vector Machines (Classification). The path string stored for this item says ML → Classification → SVM.
Related
Random forest classification and gradient boosting are the tree ensembles.