Hi,
I have developed several volatility models for international arrivals from several countries using SARIMA-GARCH and SARIMA-GJR methods assuming a normal distribution in the estimation process. However, when I checked the normality of the residuals of each of the models, majority of the residuals are not normally distributed. So now I have a few questions.
1.Is normality of residuals a must in this context? If so how can I make it normally distributed?
2. Can I assume a student-t distribution or GED distribution in the estimation process allowing fore more flexibility in the model? or is there any other suitable method?
I used Eview 10 for estimations.
Much appreciated if anyone could advise in this regard.
Kind regards
Thushara
In Eviews, you can assume t-distribution for your data. As I remember some researchers have done sensitivity analysis of ARMA to normality, and they concluded that it is enough to have at least the data close to be normally distributed.
EViews has an option only for symmetric heavy-tailed distributions like Student's t or GED where the tail parameters can be estimated or fixed within the maximum likelihood technique. You may try your model with Gaussian, Student's t or GED. Usually, Student's or GED has slightly preferred to Gaussian in terms of information criteria.
Thank you Akram Shavkatovich Hasanov . Yeah you're right. I've estimated the models under all those three distributions. Can I use AIC or SIC to select the best distribution out of those three for a particular model?
Thank you
Thushara
Yes, that is right. This what one does in practice. EViews output returns three info crit: AIC, SIC, and Hannan Quinn.
- Badges
- Science topic
- Similar topics
- Engineering
- Modeling