tvgarch-package: Time Varying GARCH Modelling

Description

Simulation, estimation and inference for univariate and multivariate TV(s)-GARCH(p,q,r)-X models, where s indicates the number and shape of the transition functions, p is the ARCH order, q is the GARCH order, r is the asymmetry order, and 'X' indicates that covariates can be included; see Campos-Martins and Sucarrat (2024) <doi:10.18637/jss.v108.i09>. The TV long-term component, as in the multiplicative TV-GARCH model of Amado and Terasvirta (2013) <doi:10.1016/j.jeconom.2013.03.006>, introduces non-stationarity whereas the GARCH-X short-term component describes conditional heteroscedasticity. Maximisation by parts leads to consistent and asymptotically normal estimates. In the multivariate case, conditional variances are estimated equation by equation and dynamic conditional correlations are allowed.

Arguments

Author

Susana Campos-Martins, https://sites.google.com/site/susanacamposmartins

Maintainer: Susana Campos-Martins
Contributor: Genaro Sucarrat

Details

Package:	tvgarch
Type:	Package
Version:	2.4.3
Date:	2025-09-01
License:	GPL>=2

References

Cristina Amado and Timo Terasvirta (2013) Modelling volatility by variance decomposition, Journal of Econometrics 175, 142-153.

Susana Campos-Martins and Genaro Sucarrat (2024) Modeling Nonstationary Financial Volatility with the R Package tvgarch, Journal of Statistical Software 108, 1-38.

Examples

Run this code

set.seed(123)

## Simulate from a TV(1)-GARCH(1,1) model (default):
ySim <- tvgarchSim(n = 1500)

## Test a GARCH(1,1) model against a TV(1)-GARCH(1,1) model:
yTest <- tvgarchTest(y = ySim)
yTest

## Estimate a TV(1)-GARCH(1,1) model (default):
yEst <- tvgarch(y = ySim)
yEst