Standard errors and confidence intervals for variable importance in random forest regression, classification, and survival

DOI10.1002/sim.7803zbMATH Open1545.62367MaRDI QIDQ6625659

Hemant Ishwaran, Min Lu

Publication date: 28 October 2024

Published in: Statistics in Medicine (Search for Journal in Brave)

zbMATH Keywords

bootstrapprediction errorsubsamplingpermutation importanceVIMPdelete-jackknife

Mathematics Subject Classification ID

Applications of statistics to biology and medical sciences; meta analysis (62P10)

Cites Work

• Unnamed Item
• Unnamed Item
• Correlation and variable importance in random forests
• Bagging predictors
• Random survival forests
• COBRA: a combined regression strategy
• Standard errors for bagged and random forest estimators
• Empirical characterization of random forest variable importance measures
• Multivariate adaptive regression splines
• On the subsample bootstrap variance estimation
• A general theory for jackknife variance estimation
• Large sample confidence regions based on subsamples under minimal assumptions
• Variable importance in binary regression trees and forests
• Consistency of random forests
• A random forest guided tour
• Recursively Imputed Survival Trees
• Consistent Estimation of the Expected Brier Score in General Survival Models with Right‐Censored Event Times
• Probability Inequalities for Sums of Bounded Random Variables
• Reinforcement Learning Trees
• Random forests

Related Items (4)

Accelerated and Interpretable Oblique Random Survival Forests ⋮ Learning from high dimensional data based on weighted feature importance in decision tree ensembles ⋮ A simple approach for local and global variable importance in nonlinear regression models ⋮ Survival analysis using a 5-step stratified testing and amalgamation routine (5-STAR) in randomized clinical trials

This page was built for publication: Standard errors and confidence intervals for variable importance in random forest regression, classification, and survival