Unrestricted permutation forces extrapolation: variable importance requires at least one more model, or there is no free variable importance
From MaRDI portal
Publication:2066736
DOI10.1007/s11222-021-10057-zzbMath1477.62008arXiv1905.03151OpenAlexW3209434414MaRDI QIDQ2066736
Siyu Zhou, Giles Hooker, Lucas K. Mentch
Publication date: 14 January 2022
Published in: Statistics and Computing (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/1905.03151
permutationinterpretationfunctional ANOVAintelligibilityfeature importancepartial dependenceICE plot
Related Items (4)
Boosting the performance of anomalous diffusion classifiers with the proper choice of features ⋮ Efficient permutation testing of variable importance measures by the example of random forests ⋮ Understanding complex predictive models with ghost variables ⋮ Interpreting machine-learning models in transformed feature space with an application to remote-sensing classification
Uses Software
Cites Work
- Unnamed Item
- Unnamed Item
- 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
- Greedy function approximation: A gradient boosting machine.
- Distribution-Free Predictive Inference For Regression
- An introduction to copulas.
- Controlling the false discovery rate via knockoffs
- Empirical characterization of random forest variable importance measures
- Grouped variable importance with random forests and application to multiple functional data analysis
- Generalized Hoeffding-Sobol decomposition for dependent variables -- application to sensitivity analysis
- Sobol' Indices and Shapley Value
- Panning for Gold: ‘Model-X’ Knockoffs for High Dimensional Controlled Variable Selection
- Unbiased variable importance for random forests
- The Conditional Permutation Test for Independence While Controlling for Confounders
- Controlling Variable Selection by the Addition of Pseudovariables
- Testing Statistical Hypotheses
- Random forests
This page was built for publication: Unrestricted permutation forces extrapolation: variable importance requires at least one more model, or there is no free variable importance
