Advances and Applications in Statistics
Volume 38, Issue 1, Pages 1 - 36
(January 2014)
|
|
SUGGESTED STATISTICAL MODEL FOR DESCRIBING THE FLUCTUATIONS IN THE CONDITIONAL VARIATION WITH APPLICATION ON THE GENERAL INDEX OF THE EGYPTIAN CAPITAL MARKET
Amr Ibrahim Abdelrahman Elatraby and Ahmed Fathy Abdelaal Elwaqdy
|
Abstract: This study evaluates the performance of a group of ARCH and GARCH forecasting volatility models. The study also compares the performance of these models and tries to determine the best model according to some criteria.
The study investigates the performance of ten models to predict the volatility. They are: ARCH, GARCH and IGARCH representing symmetric models and TARCH, APARCH, TGARCH, PGARCH, EGARCH, CGARCH and CTGARCH representing asymmetric models, with three distributions (Normal, Student’s t and Generalized Error Distribution). The conditional variance was entered and also the square root of the conditional variance as explanatory variable in the conditional mean equation for each of them. Noting that we dealt the models CGARCH and CTGARCH with only first order for the two parameters: AR(p) and MA(q). This study was performed on all indices separately because these indices differ in terms of properties and range of the data used in the study.
The study suggesed the models providing accurate descriptions and forecasts. |
Keywords and phrases: |
|
Number of Downloads: 340 | Number of Views: 1032 |
|