A note on split selection bias in classification trees

DOI10.1016/S0167-9473(03)00064-1zbMATH Open1429.62264OpenAlexW2162154995WikidataQ85633944 ScholiaQ85633944MaRDI QIDQ956844FDOQ956844

Authors B. E. Eshmatov 

Publication date 26 November 2008

Published in Computational Statistics and Data Analysis (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/s0167-9473(03)00064-1

zbMATH Keywords

Kolmogorov-Smirnov statisticPearson chi-square statistic\(P\)-valueCramér \(V^{2}\) statistic

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30)

Recommendations

• Unbiased split selection for classification trees based on the Gini index
• scientific article; zbMATH DE number 1089157
• Variable selection bias in regression trees with constant fits
• Splitting variable selection for multivariate regression trees
• Improving the precision of classification trees

Cites work

• scientific article; zbMATH DE number 3860199 (Why is no real title available?)
• scientific article; zbMATH DE number 4056803 (Why is no real title available?)
• scientific article; zbMATH DE number 708500 (Why is no real title available?)
• scientific article; zbMATH DE number 1089157 (Why is no real title available?)
• Maximally Selected Chi Square Statistics
• Minimally Selected P and Other Tests for A Single Abrupt Changepoint in A Binary Sequence
• Multiple comparisons in induction algorithms
• Percentage points of a weighted Kolmogorov-Smirnov statistic

Cited in

(24)

• PERFORMANCE OF A LOCALIZED TREE SPLITTING CRITERION IN TREE AVERAGING
• Statistical issues in machine learning -- towards reliable split selection and variable measures.
• Selecting the best splits for classification trees with categorical variables
• Tree-structured scale effects in binary and ordinal regression
• An unbiased method for constructing multilabel classification trees
• Variable selection bias in regression trees with constant fits
• Generalised indirect classifiers
• An alternative pruning based approach to unbiased recursive partitioning
• Unbiased variable selection for classification trees with multivariate responses
• Unbiased variable importance for random forests
• Regression trees for longitudinal and multiresponse data
• Improving the precision of classification trees
• Confidence sets for split points in decision trees
• Tree-structured modelling of varying coefficients
• Three Steps Strategy to Search for Optimum Classification Trees
• Item-focussed trees for the identification of items in differential item functioning
• Empirical characterization of random forest variable importance measures
• Splitting variable selection for multivariate regression trees
• Maximally selected chi-squared statistics and non-monotonic associations: an exact approach based on two cutpoints
• Rasch trees: a new method for detecting differential item functioning in the Rasch model
• A tree-based modeling approach for matched case-control studies
• Variable selection for functional density trees
• A note on the interpretation of tree-based regression models
• Unbiased split selection for classification trees based on the Gini index

Describes a project that uses

Uses Software

• C4.5
• bootstrap

This page was built for publication: A note on split selection bias in classification trees

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q956844)