Simultaneous robust estimation and variable selection for partially linear additive models

MARTINEZ, ALEJANDRA; BOENTE, GRACIELA

San Pablo

Congreso; XVI Latin American Congress of Probability and Mathematical Statistics; 2023

Latin American Society of Probability and Mathematical Statistics

In partially linear additive models the response variable depends linearly on some covariates while the others enter as a sum of univariate functions. In practice, a large number of covariates may be collected and the non-significative ones should be excluded.In order to obtain simultaneously robust estimators and select the activecovariates, we introduce robust estimators that combines B−splines, robust regression estimators and a regularization procedure based on a SCAD penalty. Through simulations, we will show the advantages of the proposed methodology with the least squares-based one. Finally, we will also illustrate the robust proposal on a real data set.