'GARCH model variance equation and choosing between models
I have wheat prices in log 1st difference. I tested it for ARCH(p) effects, and ARCH effects does exists. So i built an GARCH(p,q) model.
My issue is that I don't know which GARCH model I should use. I have learnt to use the GARCH model that mitigates heteroskedasticity and have the lowest akaike information criteria. my GARCH(1,1) model does not mitigate heteroskedasticity, so I tried with higher order.
The model that mitigates heteroskedasticity was a GARCH(2,1) model.
How do i interpret if my Resid(-1)^2 is not significant, but Resid(-2)^2 and GARCH(-1) are significant in my GARCH(2,1) model variance equation. Do I include both in my Variance equation? Or do I only include Resid(-2)^2 and GARCH(-1) when I am writing my variance equation.
Also If the coefficient of GARCH or ARCH are negative, how do I interpret that? is this model still valid if the coefficient of ARCH or GARCH are negative?
Sources
This article follows the attribution requirements of Stack Overflow and is licensed under CC BY-SA 3.0.
Source: Stack Overflow
| Solution | Source |
|---|