Thibaut,

I’m guessing you are continuing to have convergence problems, though I cannot 
be sure depending on what it is you are passing as data to the function.

There is a method called ‘convergence’ which can be used on a uGARCHfit object 
(it should return 0 if ok…related to the
convergence codes of the underlying solvers).

Additionally, if you are automating the estimation, you might want to enclose 
the estimation function with a 
‘mod=try(ugarchfit(…), silent=TRUE)’ and then check that !is(mod, ’try-error’).

Regards,

Alexios
 
On 18 Feb 2014, at 15:44, tvernay <[email protected]> wrote:

> Thanks a lot for your help Alexios, the previously mentioned error has
> disappeared! 
> Now I have the same question regarding another error which I experienced and
> which I do not understand:
> 
> Error in ans$res : $ operator is invalid for atomic vectors
> 
> Is it also related to model convergence failure? Is there any input
> parameter in ugarchfit that could prevent this error from occuring?
> 
> 
> 
> --
> View this message in context: 
> http://r.789695.n4.nabble.com/understanding-an-error-from-ugarchfit-tp4684836p4685490.html
> Sent from the Rmetrics mailing list archive at Nabble.com.
> 
> _______________________________________________
> [email protected] 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.
> 

_______________________________________________
[email protected] 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.

Reply via email to