Loh, Wei-Yih; Shih, Yu-Shan Split selection methods for classification trees. (English) Zbl 1067.62545 Stat. Sin. 7, No. 4, 815-840 (1997). Summary: Classification trees based on exhaustive search algorithms tend to be biased towards selecting variables that afford 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 final 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 classification accuracy of its trees are typically comparable to those of exhaustive search. Cited in 1 ReviewCited in 52 Documents MSC: 62H30 Classification and discrimination; cluster analysis (statistical aspects) 65C60 Computational problems in statistics (MSC2010) Keywords:Decision trees, discriminant analysis, machine learning. Software:AS 136 PDFBibTeX XMLCite \textit{W.-Y. Loh} and \textit{Y.-S. Shih}, Stat. Sin. 7, No. 4, 815--840 (1997; Zbl 1067.62545)