Grouped variable importance with random forests and application to multiple functional data analysis
From MaRDI portal
(Redirected from Publication:1663198)
Abstract: The selection of grouped variables using the random forest algorithm is considered. First a new importance measure adapted for groups of variables is proposed. Theoretical insights into this criterion are given for additive regression models. Second, an original method for selecting functional variables based on the grouped variable importance measure is developed. Using a wavelet basis, it is proposed to regroup all of the wavelet coefficients for a given functional variable and use a wrapper selection algorithm with these groups. Various other groupings which take advantage of the frequency and time localization of the wavelet basis are proposed. An extensive simulation study is performed to illustrate the use of the grouped importance measure in this context. The method is applied to a real life problem coming from aviation safety.
Recommendations
- Correlation and variable importance in random forests
- Empirical characterization of random forest variable importance measures
- Variable importance in binary regression trees and forests
- A computationally fast variable importance test for random forests for high-dimensional data
- A new variable selection approach using random forests
Cites work
- scientific article; zbMATH DE number 3860199 (Why is no real title available?)
- scientific article; zbMATH DE number 739533 (Why is no real title available?)
- scientific article; zbMATH DE number 2015204 (Why is no real title available?)
- scientific article; zbMATH DE number 1470722 (Why is no real title available?)
- scientific article; zbMATH DE number 845714 (Why is no real title available?)
- 10.1162/153244303322753616
- Adaptive estimation of a quadratic functional by model selection.
- Bagging predictors
- Correlation and variable importance in random forests
- Dimension reduction in functional regression with applications
- Functional Classification in Hilbert Spaces
- Functional Classification with Margin Conditions
- Functional Logistic Discrimination Via Regularized Basis Expansions
- Functional data analysis.
- Functional linear model
- Gene selection for cancer classification using support vector machines
- Ideal spatial adaptation by wavelet shrinkage
- Linear Statistical Inference and its Applications
- Model Selection and Estimation in Regression with Grouped Variables
- Nonparametric functional data analysis. Theory and practice.
- Prediction in functional linear regression
- Random forests
- Recent advances in functional data analysis and related topics. Selected papers based on the presentations at the international workshop on functional and operatorial statistics (IWFOS'2011), Santander, Spain, June 16--18, 2011.
- Stable feature selection for biomarker discovery
- The Group Lasso for Logistic Regression
- Variable and boundary selection for functional data via multiclass logistic regression modeling
- Variable selection for functional regression models via the \(L_1\) regularization
- Variable selection for multicategory SVM via adaptive sup-norm regularization
Cited in
(20)- Comments on ``Data science, big data and statistics
- Classification tree algorithm for grouped variables
- Interpretability of bi-level variable selection methods
- Understanding complex predictive models with ghost variables
- Trees, forests, and impurity-based variable importance in regression
- Pooling random forest and functional data analysis for biomedical signals supervised classification: theory and application to electrocardiogram data
- Random forest-based approach for physiological functional variable selection for driver's stress level classification
- A new derivative based importance criterion for groups of variables and its link with the global sensitivity indices
- Supervised classification of curves via a combined use of functional data analysis and tree-based methods
- Evaluating the impact of a grouping variable on job satisfaction drivers
- Functional variable selection via Gram–Schmidt orthogonalization for multiple functional linear regression
- Multivariate analysis of variance for functional data
- Grouped feature importance and combined features effect plot
- Supervised learning via ensembles of diverse functional representations: the functional voting classifier
- Functional archetype and archetypoid analysis
- Quantifying the closeness to a set of random curves via the mean marginal likelihood
- Unrestricted permutation forces extrapolation: variable importance requires at least one more model, or there is no free variable importance
- Tree-based boosting with functional data
- Testing conditional independence in supervised learning algorithms
- All models are wrong, but many are useful: learning a variable's importance by studying an entire class of prediction models simultaneously
This page was built for publication: Grouped variable importance with random forests and application to multiple functional data analysis
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1663198)
