Robust Variable Selection Criteria for the Penalized Regression

• Published in: arXiv.org
• Main Authors: Mandal, Abhijit, Ghosh, Samiran
• Format: Paper
• Language: English
• Published: Ithaca Cornell University Library, arXiv.org 29.12.2019
• Subjects: Algorithms; Computer simulation; Criteria; Data analysis; Divergence; Influence functions; Outliers (statistics); Parameter estimation; Penalty function; Regression analysis; Regression coefficients; Robustness (mathematics); Statistical analysis

We propose a robust variable selection procedure using a divergence based M-estimator combined with a penalty function. It produces robust estimates of the regression parameters and simultaneously selects the important explanatory variables. An efficient algorithm based on the quadratic approximatio...