[R-SIG-Finance] apARCH forecast using rugarch

[alexios ghalanos]

Jesper,

- There is a vignette which shows details of the formulae used for each 
model.
- For t+h (h>1) you will also need to understand something about the 
unconditional expectation of certain values conditional on the density D
i.e.  E[ ((abs(e)-gamma*e)^(delta)) * D(e, skew, shape, ...)]
- ...all of which are available in the source code which is there for 
you to investigate if you are truly interested (which is the whole point 
of open source).

Regards,
Alexios

PS you can access persistence using 'persistence(fit)' rather than 
fit at fit$persistence, and you can also access the long run variance using 
'uncvariance(fit)'.

On 04/03/2013 00:05, Jesper Hybel Pedersen wrote:
> I would like to know how to calculate sigma(T+2) >>manually<< to make
> sure I understand how rugarch works. I have estimated apARCH(1,1)-model
> and made a forecast:
>
> forc = ugarchforecast(fit, n.ahead=10)
> forc at forecast$forecast
> [[1]]
>         sigma     series
> 351 0.6670788 0.09166948
> 352 0.6799293 0.09166948
> 353 0.6900579 0.09166948
> 354 0.6981005 0.09166948
>
> By >>manually<< I mean something like in the case of sigma(T+1=351)
> where I can do:
>
> sigma_t_1=(omega+alpha*(abs(e_t)-gamma*e_t)^delta+beta*sigma_t^delta)^(1/delta)
> [using estimates]
>
> I was wondering whether it was possible utilizing the estimated
> persistence:
>
> hat(P) = fit at fit$persistence
>
>
>
> Any guidance is appreciated
>
> Best regards Jesper
>
> _______________________________________________
> R-SIG-Finance at r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-sig-finance
> -- Subscriber-posting only. If you want to post, subscribe first.
> -- Also note that this is not the r-help list where general R questions
> should go.
>