Tree-AS node - stopping rules

These options control how the tree is constructed. Stopping rules determine when to stop splitting specific branches of the tree. Set the minimum branch sizes to prevent splits that would create very small subgroups. Minimum records in parent branch prevents a split if the number of records in the node to be split (the parent) is less than the specified value. Minimum records in child branch prevents a split if the number of records in any branch created by the split (the child) would be less than the specified value.

• Use percentage Specify sizes in terms of percentage of overall training data.
• Use absolute value Specify sizes as the absolute numbers of records.

Minimum change in expected cell frequencies When estimating cell frequencies (for both the nominal model and the row effects ordinal model), an iterative procedure (epsilon) is used to converge on the optimal estimate used in the chi-square test for a specific split. Epsilon determines how much change must occur for iterations to continue; if the change from the last iteration is smaller than the specified value, iterations stop. If you are having problems with the algorithm not converging, you can increase this value or increase the maximum number of iterations until convergence occurs.

Maximum iterations for convergence Specifies the maximum number of iterations before stopping, whether convergence has taken place or not.