DMCA
A Root-N Consistent Backfitting Estimator for Semiparametric Additive Modelling (1999)
| Citations: | 13 - 0 self |
BibTeX
@MISC{Opsomer99aroot-n,
author = {Jean D. Opsomer and David Ruppert},
title = {A Root-N Consistent Backfitting Estimator for Semiparametric Additive Modelling},
year = {1999}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
We explore additive models that combine both parametric and nonparametric terms and propose a p n-consistent backfitting estimator for the parametric component of the model. The theoretical properties of the estimator are developed for the case with a single nonparametric term and extended to an arbitrary number of nonparametric additive terms. An estimator for the optimal bandwidth making minimal use of asymptotic expressions for bias and variance is proposed, and a fast implementation algorithm for model fitting and bandwidth selection is developed. The practical behavior of the estimator and bandwidth selection is illustrated by simulation experiments. Key Words: local polynomial regression, bandwidth selection, EBBS, partially linear model. 1 Introduction Additive models are a popular and flexible class of nonparametric regression methods (Hastie and Tibshirani (1990)), which assume that the conditional mean function can be represented as E(Y jZ 1 ; : : : ; ZD ) = m 1 (Z 1 ) + ...
Keyphrases
root-n consistent backfitting estimator bandwidth selection semiparametric additive modelling nonparametric term linear model optimal bandwidth model fitting single nonparametric term additive model key word asymptotic expression minimal use nonparametric additive term nonparametric regression method n-consistent backfitting estimator simulation experiment flexible class fast implementation algorithm local polynomial regression arbitrary number parametric component introduction additive model theoretical property conditional mean function practical behavior
