On Variable Screening in Multiple Nonparametric Regression Model

TL;DR

This paper introduces a variable screening method for multiple nonparametric regression models, leveraging the partial derivatives of the regression function to identify irrelevant variables, with theoretical and practical validation.

Contribution

It proposes a novel variable screening approach based on partial derivatives, applicable when error variance is known or unknown, with demonstrated effectiveness on simulated and real data.

Findings

Method effectively identifies irrelevant variables.

Theoretical properties established for different error variance scenarios.

Validated on interdisciplinary datasets.

Abstract

In this article, we study the problem of variable screening in multiple nonparametric regression model. The proposed methodology is based on the fact that the partial derivative of the regression function with respect to the irrelevant variable should be negligible. The Statistical property of the proposed methodology is investigated under both cases : (i) when the variance of the error term is known, and (ii) when the variance of the error term is unknown. Moreover, we establish the practicality of our proposed methodology for various simulated and real data related to interdisciplinary sciences such as Economics, Finance and other sciences.