论文信息 - Decision trees for binary classification variables grow equally with the Gini impurity measure and Pearson's chi-square test - 字舞流文

Decision trees for binary classification variables grow equally with the Gini impurity measure and Pearson's chi-square test

We show that for binary classification variables, Gini and Pearson purity measures yield exactly the same tree, provided all the other parameters of the algorithms are identical. A counter-example for ternary classification variables is given.

Larry A. Lambe | Johannes Grabmeier | J. Grabmeier | L. Lambe

[1] Ian Witten,et al. Data Mining , 2000 .

[2] Jiawei Han,et al. Data Mining: Concepts and Techniques , 2000 .

[3] Ian H. Witten,et al. Data mining: practical machine learning tools and techniques with Java implementations , 2002, SGMD.

[4] Yongjian Fu,et al. Data mining , 1997 .

[5] Leo Breiman,et al. Classification and Regression Trees , 1984 .

[6] Kate Smith-Miles,et al. Maximum-entropy estimated distribution model for classification problems , 2006, Int. J. Hybrid Intell. Syst..

[7] Jorma Rissanen,et al. SLIQ: A Fast Scalable Classifier for Data Mining , 1996, EDBT.

[8] Doheon Lee,et al. Improving Classification Accuracy of Decision Trees for Different Abstraction Levels of Data , 2005, Int. J. Data Warehous. Min..

[9] Lipo Wang,et al. Data dimensionality reduction with application to improving classification performance and explaining concepts of data sets , 2005, Int. J. Bus. Intell. Data Min..

[10] Kilian Stoffel,et al. Theoretical Comparison between the Gini Index and Information Gain Criteria , 2004, Annals of Mathematics and Artificial Intelligence.

[11] Kate Smith-Miles,et al. Kernal Width Selection for SVM Classification: A Meta-Learning Approach , 2005, Int. J. Data Warehous. Min..

[12] J. Ross Quinlan,et al. Induction of Decision Trees , 1986, Machine Learning.