Robust Variable and Interaction Selection for Logistic Regression and General Index Models
From MaRDI portal
Publication:5229910
Abstract: We propose Stepwise cOnditional likelihood variable selection for Discriminant Analysis (SODA) to detect both main and quadratic interaction effects in logistic regression and quadratic discriminant analysis (QDA) models. In the forward stage, SODA adds in important predictors evaluated based on their overall contributions, whereas in the backward stage SODA removes unimportant terms so as to optimize the extended Bayesian Information Criterion (EBIC). Compared with existing methods on QDA variable selections, SODA can deal with high-dimensional data with the number of predictors much larger than the sample size and does not require the joint normality assumption on predictors, leading to much enhanced robustness. We further extend SODA to conduct variable selection and model fitting for multiple index models. Compared with existing variable selection methods based on the Sliced Inverse Regression (SIR) (Li 1991), SODA requires neither the linearity nor the constant variance condition and is much more robust. Our theoretical analyses establish the variable-selection consistency of SODA under high-dimensional settings, and our simulation studies as well as real-data applications demonstrate superior performances of SODA in dealing with non-Gaussian design matrices in both classification problems and multiple index models.
Recommendations
- Variable selection for general index models via sliced inverse regression
- Robust variable selection in the logistic regression model
- Robust direction identification and variable selection in high dimensional general single-index models
- scientific article; zbMATH DE number 6468204
- Model-Free Variable Selection
Cites work
- scientific article; zbMATH DE number 5957408 (Why is no real title available?)
- scientific article; zbMATH DE number 3136275 (Why is no real title available?)
- scientific article; zbMATH DE number 845714 (Why is no real title available?)
- A Model Selection Approach for the Identification of Quantitative Trait Loci in Experimental Crosses
- A Permutation Approach to Testing Interactions for Binary Response by Comparing Correlations Between Classes
- A direct approach to sparse discriminant analysis in ultra-high dimensions
- A direct estimation approach to sparse linear discriminant analysis
- A lasso for hierarchical interactions
- CODA: high dimensional copula discriminant analysis
- Correlation Pursuit: Forward Stepwise Variable Selection for Index Models
- Empirical Bayes estimates for large-scale prediction problems
- Estimating the dimension of a model
- Extended BIC for small-\(n\)-large-\(P\) sparse GLM
- Extended Bayesian information criteria for model selection with large model spaces
- Feature screening via distance correlation learning
- Fisher lecture: Dimension reduction in regression
- Forward regression for ultra-high dimensional variable screening
- High-dimensional Ising model selection using \(\ell _{1}\)-regularized logistic regression
- High-dimensional classification using features annealed independence rules
- High-dimensional variable selection
- Innovated interaction screening for high-dimensional nonlinear classification
- Large-scale inference. Empirical Bayes methods for estimation, testing, and prediction
- Model-Free Variable Selection
- On BIC's selection consistency for discriminant analysis
- On consistency and sparsity for sliced inverse regression in high dimensions
- On model selection consistency of the elastic net when \(p \gg n\)
- Optimal classification in sparse Gaussian graphic model
- Penalized classification using Fisher's linear discriminant
- Random forests
- Regularization and Variable Selection Via the Elastic Net
- Regularized linear discriminant analysis and its application in microarrays
- Sliced Inverse Regression for Dimension Reduction
- Sparse linear discriminant analysis by thresholding for high dimensional data
- Sparse sufficient dimension reduction
- The sliced inverse regression algorithm as a maximum likelihood procedure
- Variable selection and updating in model-based discriminant analysis for high dimensional data with food authenticity applications
- Variable selection for general index models via sliced inverse regression
- Variable selection in model-based discriminant analysis
Cited in
(12)- Structure learning via unstructured kernel-based M-estimation
- Robust variable selection in the logistic regression model
- Sparse Learning and Structure Identification for Ultrahigh-Dimensional Image-on-Scalar Regression
- scientific article; zbMATH DE number 7370562 (Why is no real title available?)
- An efficient model-free approach to interaction screening for high dimensional data
- Interaction screening for high-dimensional heterogeneous data via robust hybrid metrics
- RaSE: A Variable Screening Framework via Random Subspace Ensembles
- Unified model-free interaction screening via CV-entropy filter
- The Kendall interaction filter for variable interaction screening in high dimensional classification problems
- Robust variable selection with application to quality of life research
- Interaction screening via Kendall's rank correlation for imbalanced multi-class classification
- BOLT-SSI: A Statistical Approach to Screening Interaction Effects for Ultra-High Dimensional Data
This page was built for publication: Robust Variable and Interaction Selection for Logistic Regression and General Index Models
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5229910)
