Bayesian bandwidth estimation in nonparametric time-varying coefficient models

Tingting Cheng, Jiti Gao, Xibin Zhang

Research output: Contribution to journalArticleResearchpeer-review

Abstract

Bandwidth plays an important role in determining the performance of nonparametric estimators, such as the local constant estimator. In this article, we propose a Bayesian approach to bandwidth estimation for local constant estimators of time-varying coefficients in time series models. We establish a large sample theory for the proposed bandwidth estimator and Bayesian estimators of the unknown parameters involved in the error density. A Monte Carlo simulation study shows that (i) the proposed Bayesian estimators for bandwidth and parameters in the error density have satisfactory finite sample performance; and (ii) our proposed Bayesian approach achieves better performance in estimating the bandwidths than the normal reference rule and cross-validation. Moreover, we apply our proposed Bayesian bandwidth estimation method for the time-varying coefficient models that explain Okun’s law and the relationship between consumption growth and income growth in the U.S. For each model, we also provide calibrated parametric forms of the time-varying coefficients. Supplementary materials for this article are available online.

Original languageEnglish
Pages (from-to)1-12
Number of pages12
JournalJournal of Business and Economic Statistics
Volume37
Issue number1
DOIs
Publication statusPublished - Jan 2019

Keywords

  • bandwidth
  • local constant estimator
  • Markov chain Monte Carlo

Cite this

@article{9ca91a21b60841d79e741e89fdb3e782,
title = "Bayesian bandwidth estimation in nonparametric time-varying coefficient models",
abstract = "Bandwidth plays an important role in determining the performance of nonparametric estimators, such as the local constant estimator. In this article, we propose a Bayesian approach to bandwidth estimation for local constant estimators of time-varying coefficients in time series models. We establish a large sample theory for the proposed bandwidth estimator and Bayesian estimators of the unknown parameters involved in the error density. A Monte Carlo simulation study shows that (i) the proposed Bayesian estimators for bandwidth and parameters in the error density have satisfactory finite sample performance; and (ii) our proposed Bayesian approach achieves better performance in estimating the bandwidths than the normal reference rule and cross-validation. Moreover, we apply our proposed Bayesian bandwidth estimation method for the time-varying coefficient models that explain Okun’s law and the relationship between consumption growth and income growth in the U.S. For each model, we also provide calibrated parametric forms of the time-varying coefficients. Supplementary materials for this article are available online.",
keywords = "bandwidth, local constant estimator, Markov chain Monte Carlo",
author = "Tingting Cheng and Jiti Gao and Xibin Zhang",
year = "2019",
month = "1",
doi = "10.1080/07350015.2016.1255216",
language = "English",
volume = "37",
pages = "1--12",
journal = "Journal of Business and Economic Statistics",
issn = "0735-0015",
publisher = "Taylor & Francis",
number = "1",

}

Bayesian bandwidth estimation in nonparametric time-varying coefficient models. / Cheng, Tingting; Gao, Jiti; Zhang, Xibin.

In: Journal of Business and Economic Statistics, Vol. 37, No. 1, 01.2019, p. 1-12.

Research output: Contribution to journalArticleResearchpeer-review

TY - JOUR

T1 - Bayesian bandwidth estimation in nonparametric time-varying coefficient models

AU - Cheng, Tingting

AU - Gao, Jiti

AU - Zhang, Xibin

PY - 2019/1

Y1 - 2019/1

N2 - Bandwidth plays an important role in determining the performance of nonparametric estimators, such as the local constant estimator. In this article, we propose a Bayesian approach to bandwidth estimation for local constant estimators of time-varying coefficients in time series models. We establish a large sample theory for the proposed bandwidth estimator and Bayesian estimators of the unknown parameters involved in the error density. A Monte Carlo simulation study shows that (i) the proposed Bayesian estimators for bandwidth and parameters in the error density have satisfactory finite sample performance; and (ii) our proposed Bayesian approach achieves better performance in estimating the bandwidths than the normal reference rule and cross-validation. Moreover, we apply our proposed Bayesian bandwidth estimation method for the time-varying coefficient models that explain Okun’s law and the relationship between consumption growth and income growth in the U.S. For each model, we also provide calibrated parametric forms of the time-varying coefficients. Supplementary materials for this article are available online.

AB - Bandwidth plays an important role in determining the performance of nonparametric estimators, such as the local constant estimator. In this article, we propose a Bayesian approach to bandwidth estimation for local constant estimators of time-varying coefficients in time series models. We establish a large sample theory for the proposed bandwidth estimator and Bayesian estimators of the unknown parameters involved in the error density. A Monte Carlo simulation study shows that (i) the proposed Bayesian estimators for bandwidth and parameters in the error density have satisfactory finite sample performance; and (ii) our proposed Bayesian approach achieves better performance in estimating the bandwidths than the normal reference rule and cross-validation. Moreover, we apply our proposed Bayesian bandwidth estimation method for the time-varying coefficient models that explain Okun’s law and the relationship between consumption growth and income growth in the U.S. For each model, we also provide calibrated parametric forms of the time-varying coefficients. Supplementary materials for this article are available online.

KW - bandwidth

KW - local constant estimator

KW - Markov chain Monte Carlo

UR - http://www.scopus.com/inward/record.url?scp=85020723546&partnerID=8YFLogxK

U2 - 10.1080/07350015.2016.1255216

DO - 10.1080/07350015.2016.1255216

M3 - Article

VL - 37

SP - 1

EP - 12

JO - Journal of Business and Economic Statistics

JF - Journal of Business and Economic Statistics

SN - 0735-0015

IS - 1

ER -