Choose the splitting method to generate your decision tree. You can compare the results from both splitting methods to determine the best choice for your application.
Least
squared error: The least squared error method is the default method that works well across many applications. The least squared error method minimizes the sum of the squared errors.
Least absolute deviation: The least absolute deviation method minimizes the sum of absolute values of errors.
Criterion for selecting optimal tree
When Least
squared error is the criterion for the node splitting method, choose between these criteria to produce the tree in the results. You can compare results from different trees to determine the best choice for your application.
Maximum
R-squared
Select this option to display results for the tree with the maximum R-squared value.
Within K standard
errors of maximum R-squared; K=
Select this option to have Minitab choose the smallest tree with an R2 value that falls within K standard errors of the tree with the maximum R2 value. By default, K=1, so the tree in the results is the smallest regression tree with an R2 value within 1 standard error of the maximum R2 value.
When Least absolute deviation is selected as the node splitting method, choose between these criteria to select the tree in the results. You can compare the results from different trees to determine the best choice for your application.
Least mean
absolute deviation
Select this option to display results for the tree with the least mean absolute deviation.
Within K
standard errors of least mean absolute deviation; K=
Select this option to have Minitab choose a tree with a mean absolute deviation value that falls within K standard errors of the tree with the least mean absolute deviation value. By default, K=1, so the tree in the results is the smallest regression tree with a mean absolute deviation value within 1 standard error of the least absolute deviation value.
Number of
surrogates for a predictor with missing values
Enter the number of surrogates that Minitab searches for when a predictor has missing values. When many predictors have similar missing value patterns, you should increase the number of surrogates.
This number represents the maximum number of surrogates that will be searches for; however, this number of surrogates may not actually be found.
The default value is 10.
Minimum
number of cases to split an internal node
Enter a value to represent the minimum number of cases an internal node to be split. The default is 10. With larger sample sizes, you may want to increase this minimum. For example, if an internal node has 10 or more cases, Minitab tries to perform a split. If the internal node has 9 cases or less, Minitab does not try to perform a split.
The internal node limit must be at least twice the terminal node limit, but larger ratios are better. Internal node limits of at least 3 times terminal node limits allow a reasonable number of splitters.
Minimum
number of cases allowed for a terminal node
Enter a value to represent the minimum number of cases that can be separated into a terminal node. The default is 3. With larger sample sizes, you may want to increase this minimum. For example, if a split would create a node with less than 3 cases, Minitab does not perform a split.
Maximum tree
depth
Enter a value to represent the maximum depth of a tree. The root node corresponds to a depth of 1. If you want to be sure to get the best tree, you need to allow for a deeper tree, even though it may slow down the processing.
Weights
Enter a column that contains the case weights. The column must have the same number of rows as the response column. Values must be ≥ 0. Minitab omits rows that contain missing values or zeros from the analysis.
