Title: Penalized M-estimators in logistic regression
Authors: Ana Maria Bianco - Universidad de Santiago de Compostela (Spain) [presenting]
Graciela Boente - Universidad de Buenos Aires (Argentina)
Gonzalo Chebi - Universidad de Buenos Aires and CONICET (Argentina)
Abstract: The problem of variable selection in logistic regression is crucial when the number of variables is high. We introduce a family of penalized M-type estimators for logistic regression that are stable against atypical data. Theoretical results regarding oracle properties are studied. A numerical study that illustrates the finite sample behaviour of the proposal is presented.