[KSCI] Korea Science Citation Index Service

http://dx.doi.org/10.5351/CKSS.2003.10.2.471

A Recursive Partitioning Rule for Binary Decision Trees

Kim, Sang-Guin (Division of Economics, Kyonggi University)

Publication Information

Communications for Statistical Applications and Methods / v.10, no.2, 2003 , pp. 471-478 More about this Journal

Abstract

In this paper, we reconsider the Kolmogorov-Smirnoff distance as a split criterion for binary decision trees and suggest an algorithm to obtain the Kolmogorov-Smirnoff distance more efficiently when the input variable have more than three categories. The Kolmogorov-Smirnoff distance is shown to have the property of exclusive preference. Empirical results, comparing the Kolmogorov-Smirnoff distance to the Gini index, show that the Kolmogorov-Smirnoff distance grows more accurate trees in terms of misclassification rate.

Keywords

Komogorov-Smirnoff distance; Binary decision tree; Split criterion;

Citations & Related Records

Reference

1	Asymptotically efficient, computationally feasible solutions to the classification problem / [ Gordon,L.;Olshen,R.A. ] / Annals of Statistics DOI ScienceOn
2	Tree-based models / [ Clark,L.A.;Pregibon,D.;J.M.Chambers(ed.);T.J.Hastie(ed.) ] / Statistical Models in S
3	/ [ Quinlan,J.R. ] / C4.5: Programs for Machine Learning
4	A recursive partitioning decision rule for nonparametric classification / [ Friedman,J.H. ] / IEEE Transactions of Computers DOI ScienceOn
5	A new criterion in selection and discretization of attributes for generation of decision trees / [ 전병환;김창수;송홍엽;김재희 ] / IEEE Transactions on Pattern Analysis and Machine Intelligence DOI ScienceOn
6	Selecting the best splits for classification trees with categorical variables / [ Shih,Y.S. ] / Statistics & Probability Letters DOI ScienceOn
7	Measures of association for cross-classifications / [ Goodman,L.A.;Kruskal,W.H. ] / Journal of the American Statistical Association DOI ScienceOn
8	/ [ Breiman,L.;Friedman,J.H.;Olshen,R.A.;Stone,C.J. ] / Classification and Regression Trees
9	An exploratory technique for investigation large quantities of categorical data / [ Kass,G.V. ] / Applied Statistics DOI ScienceOn
10	Block diagrams and splitting criteria for classification trees / [ Taylor,P.C.;Silverman,B.W. ] / Statistics and Computing DOI
11	/ [ Merz,C.J.;Murphy,P.M. ] / UCI Repository of Machine Learning Databases
12	A fast splitting procedure for classification trees / [ Mola,F.;Siciliano,R. ] / Statistics and Computing DOI ScienceOn
13	A combined nonparametric approach to feature selection and binary decision tree design / [ Rounds,E.M. ] / Pattern Recognition DOI ScienceOn