A range-based GARCH model for forecasting financial volatility
A new variant of the ARCH class of models for forecasting the conditional variance, to be called the Generalized AutoRegressive Conditional Heteroskedasticity Parkinson Range (GARCH-PARK-R) model, is proposed. The GARCH-PARK-R model, utilizing the extreme values, is a good alternative to the “realized volatility” model which requires a large amount of intra-daily data that remain relatively costly and are not readily available. The estimates of the GARCH-PARK-R model are derived using the Quasi-Maximum Likelihood Estimation (QMLE). The results suggest that the GARCHPARK- R model is a good middle ground between intra-daily models, such as the realized volatility, and inter-daily models, such as the ARCH class. The forecasting performance of the models is evaluated using the daily Philippine Peso-U.S. Dollar exchange rate from January 1997 to December 2003.
Volume (Year): 40 (2003)
Issue (Month): 2 (December)
|Contact details of provider:|| Postal: |
Web page: http://www.econ.upd.edu.ph/
More information through EDIRC
When requesting a correction, please mention this item's handle: RePEc:phs:prejrn:v:40:y:2003:i:2:p:73-90. See general information about how to correct material in RePEc.
For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: (Reuben T. Campos)
If references are entirely missing, you can add them using this form.