Filter-type variable selection based on information measures for regression tasks

DOI10.3390/E14020323zbMATH Open1306.62177OpenAlexW2017845276MaRDI QIDQ405995FDOQ405995

Authors: Pedro Latorre Carmona, José Martínez Sotoca, Filiberto Pla 

Publication date: 8 September 2014

Published in: Entropy (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.3390/e14020323

Recommendations

• 10.1162/153244303322753616
• Variable selection via a multi-stage strategy
• Publication:4723072
• Variable selection for regression models
• Performances of some high dimensional regression methods

zbMATH Keywords

variable selectionconditional mutual information

Mathematics Subject Classification ID

Statistical aspects of information-theoretic topics (62B10) Classification and discrimination; cluster analysis (statistical aspects) (62H30) Linear inference, regression (62J99) Measures of information, entropy (94A17)

Cites Work

• Title not available (Why is that?)
• Regularization and Variable Selection Via the Elastic Net
• Hedonic housing prices and the demand for clean air
• Remarks on Some Nonparametric Estimates of a Density Function
• Estimation of conditional densities and sensitivity measures in nonlinear dynamical systems
• Supervised feature selection by clustering using conditional mutual information-based distances
• On the Interplay Between Conditional Entropy and Error Probability
• Approximating conditional density functions using dimension reduction
• Fast kernel conditional density estimation: a dual-tree Monte Carlo approach
• SVM Multiregression for Nonlinear Channel Estimation in Multiple-Input Multiple-Output Systems

Cited In (2)

• Optimum simultaneous discretization with data grid models in supervised classification: a Bayesian model selection approach
• Information criteria for variable selection under sparsity

Uses Software

• ITIP

This page was built for publication: Filter-type variable selection based on information measures for regression tasks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q405995)