In PROC HPSPLIT for classification trees, which impurity measure is the default splitting criterion?
Select an answer to reveal the explanation.
Short Explanation and Infographic
Here's the deal — a is correct because PROC HPSPLIT uses Gini impurity as its default splitting criterion for classification trees. The Gini impurity measures the probability that a randomly chosen element from the node would be incorrectly classified if randomly labeled according to the node distribution.
Full explanation below image
Full Explanation
A is correct because PROC HPSPLIT uses Gini impurity as its default splitting criterion for classification trees. The Gini impurity measures the probability that a randomly chosen element from the node would be incorrectly classified if randomly labeled according to the node distribution. B (information gain/entropy) is the criterion used by ID3/C4.5 algorithms and can be selected via CRITERION=ENTROPY in some SAS procedures. C (chi-square) is used in CHAID-style trees. D (variance reduction) is used for regression trees.