Forecasting the weekly time-varying beta of UK firms: GARCH models vs Kalman filter method
Forecasting the weekly time-varying beta of UK firms: GARCH models vs Kalman filter method
This paper investigates the forecasting ability of three different GARCH models and the Kalman filter method. The three GARCH models applied are the bivariate GARCH, BEKK GARCH, and GARCH-GJR. Forecast errors based on twenty UK company’s weekly stock return (based on time-vary beta) forecasts are employed to evaluate out-of-sample forecasting ability of both the GARCH models and the Kalman method. Measures of forecast errors overwhelmingly support the Kalman filter approach. Among the GARCH models, GJR appears to provide somewhat more accurate forecasts than the two other GARCH models.
forecasting, Kalman filter, GARCH, volatility
437-444
Choudhry, Taufiq
6fc3ceb8-8103-4017-b3b5-2d38efa57728
Wu, Hao
8d0e3477-dc5a-4ce8-8121-991ad1bbb48d
June 2009
Choudhry, Taufiq
6fc3ceb8-8103-4017-b3b5-2d38efa57728
Wu, Hao
8d0e3477-dc5a-4ce8-8121-991ad1bbb48d
Choudhry, Taufiq and Wu, Hao
(2009)
Forecasting the weekly time-varying beta of UK firms: GARCH models vs Kalman filter method.
European Journal of Finance, 15 (3-4), .
(doi:10.1080/13518470802604499).
Abstract
This paper investigates the forecasting ability of three different GARCH models and the Kalman filter method. The three GARCH models applied are the bivariate GARCH, BEKK GARCH, and GARCH-GJR. Forecast errors based on twenty UK company’s weekly stock return (based on time-vary beta) forecasts are employed to evaluate out-of-sample forecasting ability of both the GARCH models and the Kalman method. Measures of forecast errors overwhelmingly support the Kalman filter approach. Among the GARCH models, GJR appears to provide somewhat more accurate forecasts than the two other GARCH models.
Text
EJF-paper_v2.doc
- Other
More information
Published date: June 2009
Keywords:
forecasting, Kalman filter, GARCH, volatility
Identifiers
Local EPrints ID: 147385
URI: http://eprints.soton.ac.uk/id/eprint/147385
ISSN: 1351-847X
PURE UUID: 2c0405d5-4789-42d6-9784-da628ad1864f
Catalogue record
Date deposited: 26 Apr 2010 08:34
Last modified: 14 Mar 2024 02:44
Export record
Altmetrics
Contributors
Author:
Hao Wu
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics
