Panel nonparametric regression with fixed effects

Jungyoon Lee; Peter M Robinson

doi:10.1016/j.jeconom.2015.03.004

Panel nonparametric regression with fixed effects

Jungyoon Lee, Peter M Robinson

Department of Economics

Research output: Contribution to journal › Article › peer-review

Abstract

Nonparametric regression is developed for data with both a temporal and a cross-sectional dimension. The model includes additive, unknown, individual-specific components and allows also for cross-sectional and temporal dependence and conditional heteroscedasticity. A simple nonparametric estimate is shown to be dominated by a GLS-type one. Asymptotically optimal bandwidth choices are justified for both estimates. Feasible optimal bandwidths, and feasible optimal regression estimates, are also asymptotically justified. Finite sample performance is examined in a Monte Carlo study.

Original language	English
Pages (from-to)	346-362
Number of pages	17
Journal	Journal of Econometrics
Volume	188
Issue number	2
Early online date	11 Mar 2015
DOIs	https://doi.org/10.1016/j.jeconom.2015.03.004
Publication status	Published - Oct 2015

Access to Document

10.1016/j.jeconom.2015.03.004Licence: CC BY

http://www.sciencedirect.com/science/article/pii/S0304407615000731Licence: CC BY

Cite this

@article{daefb13e4fed40408f46699207b8485e,

title = "Panel nonparametric regression with fixed effects",

abstract = "Nonparametric regression is developed for data with both a temporal and a cross-sectional dimension. The model includes additive, unknown, individual-specific components and allows also for cross-sectional and temporal dependence and conditional heteroscedasticity. A simple nonparametric estimate is shown to be dominated by a GLS-type one. Asymptotically optimal bandwidth choices are justified for both estimates. Feasible optimal bandwidths, and feasible optimal regression estimates, are also asymptotically justified. Finite sample performance is examined in a Monte Carlo study.",

author = "Jungyoon Lee and Robinson, {Peter M}",

year = "2015",

month = oct,

doi = "10.1016/j.jeconom.2015.03.004",

language = "English",

volume = "188",

pages = "346--362",

journal = "Journal of Econometrics",

issn = "0304-4076",

publisher = "Elsevier BV",

number = "2",

}

TY - JOUR

T1 - Panel nonparametric regression with fixed effects

AU - Lee, Jungyoon

AU - Robinson, Peter M

PY - 2015/10

Y1 - 2015/10

N2 - Nonparametric regression is developed for data with both a temporal and a cross-sectional dimension. The model includes additive, unknown, individual-specific components and allows also for cross-sectional and temporal dependence and conditional heteroscedasticity. A simple nonparametric estimate is shown to be dominated by a GLS-type one. Asymptotically optimal bandwidth choices are justified for both estimates. Feasible optimal bandwidths, and feasible optimal regression estimates, are also asymptotically justified. Finite sample performance is examined in a Monte Carlo study.

AB - Nonparametric regression is developed for data with both a temporal and a cross-sectional dimension. The model includes additive, unknown, individual-specific components and allows also for cross-sectional and temporal dependence and conditional heteroscedasticity. A simple nonparametric estimate is shown to be dominated by a GLS-type one. Asymptotically optimal bandwidth choices are justified for both estimates. Feasible optimal bandwidths, and feasible optimal regression estimates, are also asymptotically justified. Finite sample performance is examined in a Monte Carlo study.

U2 - 10.1016/j.jeconom.2015.03.004

DO - 10.1016/j.jeconom.2015.03.004

M3 - Article

SN - 0304-4076

VL - 188

SP - 346

EP - 362

JO - Journal of Econometrics

JF - Journal of Econometrics

IS - 2

ER -