[R-SIG-Finance] rugarch convergence problem

[alexios ghalanos]

Hi,

Cannot replicate the problem on my system. All series converge.
See this thread for hints:
https://stat.ethz.ch/pipermail/r-sig-finance/2014q3/012595.html

Regards,

Alexios

PS In anticipation of a further question, once you update the packages,
try using 'numderiv.control = list(hess.zero.tol=1e-7)' in the ugarchfit
function to get more sensible standard errors or
pre-multiply the returns by 100.
Also consider these 2 issues:
>length(which((Currencyret$SEK*Currencyret$CHF)<0))/nrow(Currencyret)
[1] 0.2463651
>pacf(Currencyret$SEK*Currencyret$CHF)


On 01/08/2014 01:44, Cabot_Bear wrote:
> Hi, Alexios
> 
> I am having convergence problem when fit a few time series using GARCH
> family models. The system is continuously reporting errors i.e. solver
> failer to converge or nonvalid 'nrow' value (too large or NA), depending on
> the length of dataset. Some previous discussions suggested various solvers,
> hence "nlminb", "gosolnp" and "nloptr" have been considered but non of them
> can resolve this problem. One typical example can be found here including a
> dataset and commands
> https://www.dropbox.com/sh/lu8haexfz254eab/AAAstEhd9ywWuovKp8FLm5STa
> 
> Many many thanks,
> 
> Marco
> 
> 
> 
> --
> View this message in context: http://r.789695.n4.nabble.com/rugarch-convergence-problem-tp4694878.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.
> 
>