A new model-free screening method, called Derivative Empirical Likelihood Independent Screening (D-ELSIS) is proposed for high-dimensional regression analysis. Without requiring a specific parametric form of the underlying data model, our method is able to identify explanatory variables that contribute to the explanation of the response variable in nonparametric and non-additive contexts. This approach is fully nonparametric and combines the estimation of marginal derivatives by the local polynomial estimator together with the empirical likelihood technique. The proposed method can be applied to variable screening problems emerging from a wide range of areas, from genomic and health science to economics, finance and machine learning. We report some simulation results in order to show that the D-ELSIS screening approach performs satisfactorily.
A Model-Free Screening Selection Approach by Local Derivative Estimation
Francesco Giordano;Sara Milito
;Maria Lucia Parrella
2021
Abstract
A new model-free screening method, called Derivative Empirical Likelihood Independent Screening (D-ELSIS) is proposed for high-dimensional regression analysis. Without requiring a specific parametric form of the underlying data model, our method is able to identify explanatory variables that contribute to the explanation of the response variable in nonparametric and non-additive contexts. This approach is fully nonparametric and combines the estimation of marginal derivatives by the local polynomial estimator together with the empirical likelihood technique. The proposed method can be applied to variable screening problems emerging from a wide range of areas, from genomic and health science to economics, finance and machine learning. We report some simulation results in order to show that the D-ELSIS screening approach performs satisfactorily.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.