A Weighted Sieve Estimator for Nonparametric Time Series Models With Nonstationary Variables

41 Pages Posted: 21 Aug 2018 Last revised: 8 Nov 2019

See all articles by Chaohua Dong

Chaohua Dong

Zhongnan University of Economics and Law

Oliver B. Linton

University of Cambridge

Bin Peng

Monash University - Department of Econometrics and Business Statistics

Date Written: July 9, 2018

Abstract

A novel and unified approach is proposed in sieve estimation to tackle the issue of unbounded support of variables in nonparametric regression models. The model em- braces time trend and both stationary and nonstationary variables that are allowed to be correlated. This approach is introduced via weighted least squares, and it im- proves the existing methodology and alleviates the requirement of related moments. As a byproduct, the requirement on the α-mixing coefficients for stationary process is reduced to the least in comparison with the literature. Central limit theorems are established for the sieve estimator and other related quantities. Monte Carlo simulation confirms the theoretical results and an empirical study is provided.

Keywords: Nonparametric regression, nonstationary variable, sieve estimation, stationary variable, time trend, unbounded support

JEL Classification: C12, C22, C32

Suggested Citation

Dong, Chaohua and Linton, Oliver B. and Peng, Bin, A Weighted Sieve Estimator for Nonparametric Time Series Models With Nonstationary Variables (July 9, 2018). Available at SSRN: https://ssrn.com/abstract=3210649 or http://dx.doi.org/10.2139/ssrn.3210649

Chaohua Dong (Contact Author)

Zhongnan University of Economics and Law ( email )

182 Nanhu Avenue
Wuhan, Hubei 430073
China

Oliver B. Linton

University of Cambridge ( email )

Faculty of Economics
Cambridge, CB3 9DD
United Kingdom

Bin Peng

Monash University - Department of Econometrics and Business Statistics ( email )

900 Dandenong Road
Caulfield East, VIC 3145
Australia

Do you have negative results from your research you’d like to share?

Paper statistics

Downloads
109
Abstract Views
678
Rank
451,035
PlumX Metrics