Logo
Munich Personal RePEc Archive

A Forecast Comparison of Financial Volatility Models: GARCH (1,1) is not Enough

Mapa, Dennis S. (2004): A Forecast Comparison of Financial Volatility Models: GARCH (1,1) is not Enough. Published in: The Philippine Statistician , Vol. 53, No. 1-4 (2004): pp. 1-10.

[thumbnail of MPRA_paper_21028.pdf]
Preview
PDF
MPRA_paper_21028.pdf

Download (149kB) | Preview

Abstract

Asset allocation and risk calculations depend largely on volatile models. The parameters of the volatility models are estimated using either the Maximum Likelihood (ML) or the Quasi-Maximum Likelihood (QML). By comparing the out-of-sample forecasting performance of 68 ARCH-type models using inter-daily data on the peso-dollar exchange rate, this study shows that it is important to correctly specify the distribution of the asset returns and not only focus on the specification of the volatility. The forecasts are compared to the Parkinson Range, an alternative to the Realized Volatility.

Atom RSS 1.0 RSS 2.0

Contact us: mpra@ub.uni-muenchen.de

This repository has been built using EPrints software.

MPRA is a RePEc service hosted by Logo of the University Library LMU Munich.