Accurate value-at-risk forecasting based on the normal-GARCH model

Authors:
Christoph Hartz;Stefan Mittnik;Marc Paolella
Affiliations:
Department of Statistics, University of Munich, Germany;Department of Statistics, University of Munich, Germany and Center for Financial Studies, Frankfurt, Germany and Ifo Institute for Economic Research, Munich, Germany;Swiss Banking Institute, University of Zurich, Switzerland
Venue:
Computational Statistics & Data Analysis
Year:
2006

Citing 3
Cited 8

The impact of general non-parametric volatility functions in multivariate GARCH models

Computational Statistics & Data Analysis
Bootstrap prediction for returns and volatilities in GARCH models

Computational Statistics & Data Analysis
Testing the stable Paretian assumption

Mathematical and Computer Modelling: An International Journal

Preface: Special Issue on Nonlinear Modelling and Financial Econometrics

Computational Statistics & Data Analysis
Saddlepoint approximations for the doubly noncentral t distribution

Computational Statistics & Data Analysis
A bootstrap approach to test the conditional symmetry in time series models

Computational Statistics & Data Analysis
Modelling nonlinearities and heavy tails via threshold normal mixture GARCH models

Computational Statistics & Data Analysis
Exchange rate prediction using hybrid neural networks and trading indicators

Neurocomputing
A comparison of GARCH models for VaR estimation

Expert Systems with Applications: An International Journal
Heavy-tailed mixture GARCH volatility modeling and Value-at-Risk estimation

Expert Systems with Applications: An International Journal
VAD Based on Kernel Smoothed Function of EGARCH Models

Wireless Personal Communications: An International Journal

Quantified Score

Hi-index	0.03

Visualization

Abstract

A resampling method based on the bootstrap and a bias-correction step is developed for improving the Value-at-Risk (VaR) forecasting ability of the normal-GARCH model. Compared to the use of more sophisticated GARCH models, the new method is fast, easy to implement, numerically reliable, and, except for having to choose a window length L for the bias-correction step, fully data driven. The results for several different financial asset returns over a long out-of-sample forecasting period, as well as use of simulated data, strongly support use of the new method, and the performance is not sensitive to the choice of L.