Local Polynomial Estimation of Time-Varying Parameters in Nonlinear Models

Publikation: Working paper › Preprint › Forskning

Standard

Local Polynomial Estimation of Time-Varying Parameters in Nonlinear Models. / Kristensen, Dennis; Lee, Young Jun.

2019.

Publikation: Working paper › Preprint › Forskning

Harvard

Kristensen, D & Lee, YJ 2019 'Local Polynomial Estimation of Time-Varying Parameters in Nonlinear Models'.

APA

Kristensen, D., & Lee, Y. J. (2019). Local Polynomial Estimation of Time-Varying Parameters in Nonlinear Models.

Vancouver

Kristensen D, Lee YJ. Local Polynomial Estimation of Time-Varying Parameters in Nonlinear Models. 2019 apr. 10.

Author

Kristensen, Dennis ; Lee, Young Jun. / Local Polynomial Estimation of Time-Varying Parameters in Nonlinear Models. 2019.

Bibtex

@techreport{50ce94044ecb48bdb625df230a39c45b,
title = "Local Polynomial Estimation of Time-Varying Parameters in Nonlinear Models",
abstract = " We develop a novel asymptotic theory for local polynomial (quasi-) maximum-likelihood estimators of time-varying parameters in a broad class of nonlinear time series models. Under weak regularity conditions, we show the proposed estimators are consistent and follow normal distributions in large samples. Our conditions impose weaker smoothness and moment conditions on the data-generating process and its likelihood compared to existing theories. Furthermore, the bias terms of the estimators take a simpler form. We demonstrate the usefulness of our general results by applying our theory to local (quasi-)maximum-likelihood estimators of a time-varying VAR's, ARCH and GARCH, and Poisson autogressions. For the first three models, we are able to substantially weaken the conditions found in the existing literature. For the Poisson autogression, existing theories cannot be be applied while our novel approach allows us to analyze it. ",
keywords = "econ.EM, math.ST, stat.TH",
author = "Dennis Kristensen and Lee, {Young Jun}",
year = "2019",
month = apr,
day = "10",
language = "Udefineret/Ukendt",
type = "WorkingPaper",

}

RIS

TY - UNPB

T1 - Local Polynomial Estimation of Time-Varying Parameters in Nonlinear Models

AU - Kristensen, Dennis

AU - Lee, Young Jun

PY - 2019/4/10

Y1 - 2019/4/10

N2 - We develop a novel asymptotic theory for local polynomial (quasi-) maximum-likelihood estimators of time-varying parameters in a broad class of nonlinear time series models. Under weak regularity conditions, we show the proposed estimators are consistent and follow normal distributions in large samples. Our conditions impose weaker smoothness and moment conditions on the data-generating process and its likelihood compared to existing theories. Furthermore, the bias terms of the estimators take a simpler form. We demonstrate the usefulness of our general results by applying our theory to local (quasi-)maximum-likelihood estimators of a time-varying VAR's, ARCH and GARCH, and Poisson autogressions. For the first three models, we are able to substantially weaken the conditions found in the existing literature. For the Poisson autogression, existing theories cannot be be applied while our novel approach allows us to analyze it.

AB - We develop a novel asymptotic theory for local polynomial (quasi-) maximum-likelihood estimators of time-varying parameters in a broad class of nonlinear time series models. Under weak regularity conditions, we show the proposed estimators are consistent and follow normal distributions in large samples. Our conditions impose weaker smoothness and moment conditions on the data-generating process and its likelihood compared to existing theories. Furthermore, the bias terms of the estimators take a simpler form. We demonstrate the usefulness of our general results by applying our theory to local (quasi-)maximum-likelihood estimators of a time-varying VAR's, ARCH and GARCH, and Poisson autogressions. For the first three models, we are able to substantially weaken the conditions found in the existing literature. For the Poisson autogression, existing theories cannot be be applied while our novel approach allows us to analyze it.

KW - econ.EM

KW - math.ST

KW - stat.TH

M3 - Preprint

BT - Local Polynomial Estimation of Time-Varying Parameters in Nonlinear Models

ER -

ID: 315408274