Split Selection Methods for Classi cation

Classiication trees based on exhaustive search algorithms tend to be biased towards selecting variables that aaord more splits. As a result, such trees should be interpreted with caution. This article presents an algorithm called QUEST that has negligible bias. Its split selection strategy shares similarities with the FACT method, but it yields binary splits and the nal tree can be selected by a direct stopping rule or by pruning. Real and simulated data are used to compare QUEST with the exhaustive search approach. QUEST is shown to be substantially faster and the size and classiication accuracy of its trees are typically comparable to those of exhaustive search.