[R-SIG-Finance] [rugarch] error in ugarchfit due to external regressors

[Alexios Ghalanos]

It doesn't matter whether the parameters appear to be numeric or not. If the solver failed to converge then the returned object cannot be used, and will not contain the full information required to be useful in other routines. 
Try a different solver or change any of a number of options available which may lead to convergence...a topic already exhaustively discussed in this forum in the past.

Alexios

On 20 Dec 2013, at 05:49 AM, Grigory <franguridi at gmail.com> wrote:

> There is indeed a warning:
> ugarchfit-->warning: solver failed to converge
> with optim giving code=1. But the estimated parameter values are numeric;
> why then the error is thrown when I am trying to use ugarchforecast() with
> this uGARCHfit object as a parameter?
> 
> Thank you for your response.
> 
> 
> alexios wrote
>> There was no error in the code...did you check the convergence of your
>> estimated object?
>> If you want more help, consider providing reproducible code as per the
>> guidelines.
>> 
>> Alexios
>> 
>> On 19/12/2013 15:50, Grigory wrote:
>>> I have the very same problem, even with 'external.regressors=NULL'
>>> option.
>>> Has it been solved already? Thank you.
>>> 
>>> 
>>> alexios wrote
>>>> Send me your exact code and dataset used (if possible) off-mailing list
>>>> and I'll take a look.
>>>> 
>>>> Alexios
>>>> 
>>>> On 26/11/2013 12:14, tvernay wrote:
>>>>> Thanks for this suggestion Alexios. I am now running the latest rugarch
>>>>> version from r-forge (1.2-9) but the error remains. Basically, this
>>>>> error
>>>>> is
>>>>> described as a ugarchfilter error, while I do not have any call to this
>>>>> routine in my code. Apparently this error comes from the ugarchfit
>>>>> function
>>>>> with external regressors, for some reason...
>>>>> 
>>>>> Cheers,
>>>>> 
>>>>> Thibaut
>>>>> 
>>>>> 
>>>>> 
>>>>> --
>>>>> View this message in context:
>>>>> http://r.789695.n4.nabble.com/rugarch-error-in-ugarchfit-due-to-external-regressors-tp4681114p4681177.html
>>>>> Sent from the Rmetrics mailing list archive at Nabble.com.
>>>>> 
>>>>> _______________________________________________
>>>>> 
>>> 
>>>> R-SIG-Finance@
>>> 
>>>> 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.
>>>>> 
>>>>> 
>>>> 
>>>> _______________________________________________
>>> 
>>>> R-SIG-Finance@
>>> 
>>>> 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.
>>> 
>>> 
>>> 
>>> 
>>> 
>>> --
>>> View this message in context:
>>> http://r.789695.n4.nabble.com/rugarch-error-in-ugarchfit-due-to-external-regressors-tp4681114p4682477.html
>>> Sent from the Rmetrics mailing list archive at Nabble.com.
>>> 
>>> _______________________________________________
>>> 
> 
>> R-SIG-Finance@
> 
>> 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.
>>> 
>>> 
>> 
>> _______________________________________________
> 
>> R-SIG-Finance@
> 
>> 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.
> 
> 
> 
> 
> 
> --
> View this message in context: http://r.789695.n4.nabble.com/rugarch-error-in-ugarchfit-due-to-external-regressors-tp4681114p4682529.html
> Sent from the Rmetrics mailing list archive at Nabble.com.
> 
> _______________________________________________
> 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.
>