Model averaging over nonparametric estimators

Daniel J. Henderson, Christopher Parmeter

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

It is known that model averaging estimators are useful when there is uncertainty governing which covariates should enter the model. We argue that in applied research there is also uncertainty as to which method one should deploy, prompting model averaging over user-defined choices. Specifically, we propose, and detail, a nonparametric regression estimator averaged over choice of kernel, bandwidth selection mechanism and local-polynomial order. Simulations and an empirical application are provided to highlight the potential benefits of the method.

Original languageEnglish (US)
Pages (from-to)539-560
Number of pages22
JournalAdvances in Econometrics
Volume36
DOIs
StatePublished - Jan 1 2016

Fingerprint

Estimator
Model averaging
Uncertainty
Applied research
Bandwidth
Simulation
Nonparametric regression
Kernel
Local polynomial
Covariates

Keywords

  • Cross-validation; kernel; local-polynomial; model averaging

ASJC Scopus subject areas

  • Economics and Econometrics

Cite this

Model averaging over nonparametric estimators. / Henderson, Daniel J.; Parmeter, Christopher.

In: Advances in Econometrics, Vol. 36, 01.01.2016, p. 539-560.

Research output: Contribution to journalArticle

@article{8ee4f7085bcd4729b964513d731fa62f,
title = "Model averaging over nonparametric estimators",
abstract = "It is known that model averaging estimators are useful when there is uncertainty governing which covariates should enter the model. We argue that in applied research there is also uncertainty as to which method one should deploy, prompting model averaging over user-defined choices. Specifically, we propose, and detail, a nonparametric regression estimator averaged over choice of kernel, bandwidth selection mechanism and local-polynomial order. Simulations and an empirical application are provided to highlight the potential benefits of the method.",
keywords = "Cross-validation; kernel; local-polynomial; model averaging",
author = "Henderson, {Daniel J.} and Christopher Parmeter",
year = "2016",
month = "1",
day = "1",
doi = "10.1108/S0731-905320160000036024",
language = "English (US)",
volume = "36",
pages = "539--560",
journal = "Advances in Econometrics",
issn = "0731-9053",
publisher = "JAI Press",

}

TY - JOUR

T1 - Model averaging over nonparametric estimators

AU - Henderson, Daniel J.

AU - Parmeter, Christopher

PY - 2016/1/1

Y1 - 2016/1/1

N2 - It is known that model averaging estimators are useful when there is uncertainty governing which covariates should enter the model. We argue that in applied research there is also uncertainty as to which method one should deploy, prompting model averaging over user-defined choices. Specifically, we propose, and detail, a nonparametric regression estimator averaged over choice of kernel, bandwidth selection mechanism and local-polynomial order. Simulations and an empirical application are provided to highlight the potential benefits of the method.

AB - It is known that model averaging estimators are useful when there is uncertainty governing which covariates should enter the model. We argue that in applied research there is also uncertainty as to which method one should deploy, prompting model averaging over user-defined choices. Specifically, we propose, and detail, a nonparametric regression estimator averaged over choice of kernel, bandwidth selection mechanism and local-polynomial order. Simulations and an empirical application are provided to highlight the potential benefits of the method.

KW - Cross-validation; kernel; local-polynomial; model averaging

UR - http://www.scopus.com/inward/record.url?scp=84975729847&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84975729847&partnerID=8YFLogxK

U2 - 10.1108/S0731-905320160000036024

DO - 10.1108/S0731-905320160000036024

M3 - Article

AN - SCOPUS:84975729847

VL - 36

SP - 539

EP - 560

JO - Advances in Econometrics

JF - Advances in Econometrics

SN - 0731-9053

ER -