The PROC HPSPLIT statement invokes the procedure. Table 15.2 summarizes the options in the PROC HPSPLIT statement.
Table 15.2: PROC HPSPLIT Statement Options
Option 
Description 

Basic Options 

Specifies the input data set 

Specifies the formatted value of the target event (decision trees) 

Specifies the number of bins for interval variables 

Sets the minimum variance for a regression tree leaf to be split 

Specifies the number of surrogate rules to create 

Specifies that variables should be split only once per branch 

Splitting Options 

Specifies the minimum number of observations per leaf 

Specifies the maximum leaves per node 

Specifies the maximum tree depth 

Specifies the number of observations per level to consider a level for splitting 

Specifies how to handle missing values in an input variable 

FastCHAID and chisquare Options 

Specifies the maximum pvalue for a split to be considered 

Enables the Bonferroni adjustment to aftersplit pvalues 

F Test Options 

Specifies the maximum pvalue for a split to be considered 

FastCHAID Options 

Specifies the minimum KolmogorovSmirnov distance 
You can specify the following options: