Select menu: Stats | Multivariate Analysis | Trees | Tree Pruning
The construction of a classification tree or a regression tree generally results in over fitting, that is it continues to extend the branches of the tree beyond the point that can be justified statistically. This menu provides a solution where you can prune the tree to remove the uninformative sub-branches.
- After you have imported your data, from the menu select
Stats | Multivariate Analysis | Trees | Tree Pruning.
- Fill in the fields as required then click Run.
This lists data structures appropriate to the current input field. The contents will change as you move from one field to the next. Double-click a name to copy it to the current input field or type the name.
Specify a tree structure for the classification or regression tree that is to be pruned.
Pointer to pruned trees
Pointer to save the trees generated during the pruning of each tree.
Specifies which items of output are to be displayed in the Output window.
|Plots accuracy of the pruned trees of each tree against number of terminal nodes in the pruned trees of each tree
|Table with accuracy of the pruned trees of each tree and number of terminal nodes in the pruned trees of each tree
|Information monitoring during pruning
Replace with pruned
Lets you replace the existing tree by the pruned tree. On clicking this button you will be prompted with a dialog to specify a new number for the tree.