I try to find an easy and understandable description of How to calculate a short-term variance in garch model, when p and q are not equal 1. Let's have a look at this video: https://www.youtube.com/watch?v=o-Kf6Y419hU&t=316s He takes as parameters
- long term variance (V)
- short term variance (sigma2)
- returns (u)
And makes me a bit confused. There is also function written in python to calculate it, but I am clearly can't get it https://github.com/bashtage/arch/blob/master/arch/univariate/recursions.pyx
Can you tell me how can I implement it based on example of garch(2,2)?