Paper #164

Title:

Weighted Kernel regression

Authors:

Pedro Delicado and Manuel del Rio

Date:

March 1996 (Revised: April 1997)

Abstract:

In the fixed design regression model, additional weights are considered for the Nadaraya--Watson and Gasser--M\"uller kernel estimators. We study their asymptotic behavior and the relationships between new and classical estimators. For a simple family of weights, and considering the IMSE as global loss criterion, we show some possible theoretical advantages. An empirical study illustrates the performance of the weighted estimators in finite samples.

Keywords:

Asymptotic behavior, fixed design, nonparametric regression, smoothing

JEL codes:

C14, C15

Area of Research:

Statistics, Econometrics and Quantitative Methods

Published in:

Communications in Statistics. Theory and methods, 26(12), 2983-2998, 1997
With the title:
Weighted nonparametric regression

Download the paper in PDF format