Unbiased split selection for classification trees based on the Gini index

DOI10.1016/j.csda.2006.12.030zbMath1452.62469OpenAlexW2110878112WikidataQ63071608 ScholiaQ63071608MaRDI QIDQ1020835

Thomas Augustin, Carolin Strobl, Anne-Laure Boulesteix

Publication date: 2 June 2009

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

Full work available at URL: https://doi.org/10.1016/j.csda.2006.12.030

zbMATH Keywords

classification treesmissing valuesGini gainvariable selection bias

Mathematics Subject Classification ID

Computational methods for problems pertaining to statistics (62-08) Classification and discrimination; cluster analysis (statistical aspects) (62H30) Applications of statistics to biology and medical sciences; meta analysis (62P10) Learning and adaptive systems in artificial intelligence (68T05)

Related Items (31)

A new variable selection approach using random forests ⋮ Stochastic dominance with imprecise information ⋮ Variable selection by random forests using data with missing values ⋮ Variable selection for functional density trees ⋮ Item-focussed trees for the identification of items in differential item functioning ⋮ A toolbox of permutation tests for structural change ⋮ Sensory analysis in the food industry as a tool for marketing decisions ⋮ Model-based recursive partitioning algorithm to penalized non-crossing multiple quantile regression for the right-censored data ⋮ A new variable importance measure for random forests with missing data ⋮ Efficient permutation testing of variable importance measures by the example of random forests ⋮ Adaptive selection of extra cutpoints -- towards reconciling robustness and interpretability in classification trees ⋮ Random forest with acceptance-rejection trees ⋮ Recursive partitioning on incomplete data using surrogate decisions and multiple imputation ⋮ Regression trees for longitudinal and multiresponse data ⋮ Addressing the problem of missing data in decision tree modeling ⋮ Unnamed Item ⋮ Unnamed Item ⋮ All Models are Wrong, but Many are Useful: Learning a Variable's Importance by Studying an Entire Class of Prediction Models Simultaneously ⋮ Improving the precision of classification trees ⋮ Unbiased variable importance for random forests ⋮ Appraisal of Performance of Three Tree-Based Classification Methods ⋮ Predicting missing values: a comparative study on non-parametric approaches for imputation ⋮ Evaluation of four multiple imputation methods for handling missing binary outcome data in the presence of an interaction between a dummy and a continuous variable ⋮ Three Steps Strategy to Search for Optimum Classification Trees ⋮ Rasch trees: a new method for detecting differential item functioning in the Rasch model ⋮ Maximally selected chi-squared statistics and non-monotonic associations: an exact approach based on two cutpoints ⋮ Editorial: Statistical learning methods including dimensionality reduction ⋮ Tree-structured scale effects in binary and ordinal regression ⋮ Empirical characterization of random forest variable importance measures ⋮ Unnamed Item ⋮ Evaluating the impact of a grouping variable on job satisfaction drivers

Uses Software

• R

Cites Work

• A note on split selection bias in classification trees
• Variable selection bias in regression trees with constant fits
• Identification of interaction patterns and classification with applications to microarray data
• Bias in information-based measures in decision tree induction
• Maximally Selected Chi Square Statistics
• Maximally Selected Chi-square Statistics for Ordinal Variables
• Maximally Selected Chi‐Square Statistics and Binary Splits of Nominal Variables
• Random forests
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item

This page was built for publication: Unbiased split selection for classification trees based on the Gini index