Department of Economics and Business Economics

Timo Teräsvirta

Modelling Conditional and Unconditional Heteroskedasticity with Smoothly Time-Varying Structure

Research output: Working paper

Standard

Modelling Conditional and Unconditional Heteroskedasticity with Smoothly Time-Varying Structure. / Amado, Christina; Teräsvirta, Timo.

Aarhus : Institut for Økonomi, Aarhus Universitet, 2008.

Research output: Working paper

Harvard

APA

CBE

MLA

Amado, Christina and Timo Teräsvirta Modelling Conditional and Unconditional Heteroskedasticity with Smoothly Time-Varying Structure. Aarhus: Institut for Økonomi, Aarhus Universitet. 2008., 56 p.

Vancouver

Author

Amado, Christina ; Teräsvirta, Timo. / Modelling Conditional and Unconditional Heteroskedasticity with Smoothly Time-Varying Structure. Aarhus : Institut for Økonomi, Aarhus Universitet, 2008.

Bibtex

@techreport{9c320550cd9411dcabe4000ea68e967b,
title = "Modelling Conditional and Unconditional Heteroskedasticity with Smoothly Time-Varying Structure",
abstract = "In this paper, we propose two parametric alternatives to the standard GARCH model.They allow the conditional variance to have a smooth time-varying structure of either ad-ditive or multiplicative type. The suggested parameterizations describe both nonlinearityand structural change in the conditional and unconditional variances where the transitionbetween regimes over time is smooth. A modelling strategy for these new time-varyingparameter GARCH models is developed. It relies on a sequence of Lagrange multipliertests, and the adequacy of the estimated models is investigated by Lagrange multipliertype misspecification tests. Finite-sample properties of these procedures and tests areexamined by simulation. An empirical application to daily stock returns and another oneto daily exchange rate returns illustrate the functioning and properties of our modellingstrategy in practice. The results show that the long memory type behaviour of the sampleautocorrelation functions of the absolute returns can also be explained by deterministicchanges in the unconditional variance.",
keywords = "Conditional heteroskedasticity; Structural change; Lagrange multiplier test;",
author = "Christina Amado and Timo Ter\{"a}svirta",
year = "2008",
language = "English",
publisher = "Institut for \{O}konomi, Aarhus Universitet",
type = "WorkingPaper",
institution = "Institut for \{O}konomi, Aarhus Universitet",

}

RIS

TY - UNPB

T1 - Modelling Conditional and Unconditional Heteroskedasticity with Smoothly Time-Varying Structure

AU - Amado,Christina

AU - Teräsvirta,Timo

PY - 2008

Y1 - 2008

N2 - In this paper, we propose two parametric alternatives to the standard GARCH model.They allow the conditional variance to have a smooth time-varying structure of either ad-ditive or multiplicative type. The suggested parameterizations describe both nonlinearityand structural change in the conditional and unconditional variances where the transitionbetween regimes over time is smooth. A modelling strategy for these new time-varyingparameter GARCH models is developed. It relies on a sequence of Lagrange multipliertests, and the adequacy of the estimated models is investigated by Lagrange multipliertype misspecification tests. Finite-sample properties of these procedures and tests areexamined by simulation. An empirical application to daily stock returns and another oneto daily exchange rate returns illustrate the functioning and properties of our modellingstrategy in practice. The results show that the long memory type behaviour of the sampleautocorrelation functions of the absolute returns can also be explained by deterministicchanges in the unconditional variance.

AB - In this paper, we propose two parametric alternatives to the standard GARCH model.They allow the conditional variance to have a smooth time-varying structure of either ad-ditive or multiplicative type. The suggested parameterizations describe both nonlinearityand structural change in the conditional and unconditional variances where the transitionbetween regimes over time is smooth. A modelling strategy for these new time-varyingparameter GARCH models is developed. It relies on a sequence of Lagrange multipliertests, and the adequacy of the estimated models is investigated by Lagrange multipliertype misspecification tests. Finite-sample properties of these procedures and tests areexamined by simulation. An empirical application to daily stock returns and another oneto daily exchange rate returns illustrate the functioning and properties of our modellingstrategy in practice. The results show that the long memory type behaviour of the sampleautocorrelation functions of the absolute returns can also be explained by deterministicchanges in the unconditional variance.

KW - Conditional heteroskedasticity; Structural change; Lagrange multiplier test;

M3 - Working paper

BT - Modelling Conditional and Unconditional Heteroskedasticity with Smoothly Time-Varying Structure

PB - Institut for Økonomi, Aarhus Universitet

CY - Aarhus

ER -