Jump-Preserving Varying-Coefficient Models for Nonlinear Time Series

Pavel Cizek, Chao Koo

Research output: Working paperDiscussion paperOther research output

488 Downloads (Pure)

Abstract

An important and widely used class of semiparametric models is formed by the varyingcoefficient models. Although the varying coefficients are traditionally assumed to be smooth functions, the varying-coefficient model is considered here with the coefficient functions containing a finite set of discontinuities. Contrary to the existing nonparametric and varying-coefficient estimation of piecewise smooth functions, the varying-coefficient models are considered here under dependence and are applicable in time series with heteroscedastic and serially correlated errors. Additionally, the conditional error variance
is allowed to exhibit discontinuities at a finite set of points too. The (uniform) consistency and asymptotic normality of the proposed estimators are established and the finite-sample performance is tested via a simulation study.
Original languageEnglish
Place of PublicationTilburg
PublisherCentER, Center for Economic Research
Number of pages75
Volume2017-017
Publication statusPublished - 22 Mar 2017

Publication series

NameCentER Discussion Paper
Volume2017-017

Fingerprint

Varying Coefficient Model
Nonlinear Time Series
Varying Coefficients
Finite Set
Discontinuity
Jump
Piecewise Smooth Functions
Uniform Consistency
Correlated Errors
Uniform Asymptotics
Semiparametric Model
Asymptotic Normality
Smooth function
Set of points
Time series
Simulation Study
Estimator
Coefficient
Model
Class

Keywords

  • change point
  • Heteroscedasticity
  • local linear fitting
  • nonlinear time series
  • varying-coefficient models

Cite this

Cizek, P., & Koo, C. (2017). Jump-Preserving Varying-Coefficient Models for Nonlinear Time Series. (CentER Discussion Paper; Vol. 2017-017). Tilburg: CentER, Center for Economic Research.
Cizek, Pavel ; Koo, Chao. / Jump-Preserving Varying-Coefficient Models for Nonlinear Time Series. Tilburg : CentER, Center for Economic Research, 2017. (CentER Discussion Paper).
@techreport{c849e96f3ad1461e96c6f095affc1053,
title = "Jump-Preserving Varying-Coefficient Models for Nonlinear Time Series",
abstract = "An important and widely used class of semiparametric models is formed by the varyingcoefficient models. Although the varying coefficients are traditionally assumed to be smooth functions, the varying-coefficient model is considered here with the coefficient functions containing a finite set of discontinuities. Contrary to the existing nonparametric and varying-coefficient estimation of piecewise smooth functions, the varying-coefficient models are considered here under dependence and are applicable in time series with heteroscedastic and serially correlated errors. Additionally, the conditional error varianceis allowed to exhibit discontinuities at a finite set of points too. The (uniform) consistency and asymptotic normality of the proposed estimators are established and the finite-sample performance is tested via a simulation study.",
keywords = "change point, Heteroscedasticity, local linear fitting, nonlinear time series, varying-coefficient models",
author = "Pavel Cizek and Chao Koo",
year = "2017",
month = "3",
day = "22",
language = "English",
volume = "2017-017",
series = "CentER Discussion Paper",
publisher = "CentER, Center for Economic Research",
type = "WorkingPaper",
institution = "CentER, Center for Economic Research",

}

Cizek, P & Koo, C 2017 'Jump-Preserving Varying-Coefficient Models for Nonlinear Time Series' CentER Discussion Paper, vol. 2017-017, CentER, Center for Economic Research, Tilburg.

Jump-Preserving Varying-Coefficient Models for Nonlinear Time Series. / Cizek, Pavel; Koo, Chao.

Tilburg : CentER, Center for Economic Research, 2017. (CentER Discussion Paper; Vol. 2017-017).

Research output: Working paperDiscussion paperOther research output

TY - UNPB

T1 - Jump-Preserving Varying-Coefficient Models for Nonlinear Time Series

AU - Cizek, Pavel

AU - Koo, Chao

PY - 2017/3/22

Y1 - 2017/3/22

N2 - An important and widely used class of semiparametric models is formed by the varyingcoefficient models. Although the varying coefficients are traditionally assumed to be smooth functions, the varying-coefficient model is considered here with the coefficient functions containing a finite set of discontinuities. Contrary to the existing nonparametric and varying-coefficient estimation of piecewise smooth functions, the varying-coefficient models are considered here under dependence and are applicable in time series with heteroscedastic and serially correlated errors. Additionally, the conditional error varianceis allowed to exhibit discontinuities at a finite set of points too. The (uniform) consistency and asymptotic normality of the proposed estimators are established and the finite-sample performance is tested via a simulation study.

AB - An important and widely used class of semiparametric models is formed by the varyingcoefficient models. Although the varying coefficients are traditionally assumed to be smooth functions, the varying-coefficient model is considered here with the coefficient functions containing a finite set of discontinuities. Contrary to the existing nonparametric and varying-coefficient estimation of piecewise smooth functions, the varying-coefficient models are considered here under dependence and are applicable in time series with heteroscedastic and serially correlated errors. Additionally, the conditional error varianceis allowed to exhibit discontinuities at a finite set of points too. The (uniform) consistency and asymptotic normality of the proposed estimators are established and the finite-sample performance is tested via a simulation study.

KW - change point

KW - Heteroscedasticity

KW - local linear fitting

KW - nonlinear time series

KW - varying-coefficient models

M3 - Discussion paper

VL - 2017-017

T3 - CentER Discussion Paper

BT - Jump-Preserving Varying-Coefficient Models for Nonlinear Time Series

PB - CentER, Center for Economic Research

CY - Tilburg

ER -

Cizek P, Koo C. Jump-Preserving Varying-Coefficient Models for Nonlinear Time Series. Tilburg: CentER, Center for Economic Research. 2017 Mar 22. (CentER Discussion Paper).