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

[alexios ghalanos]

I searched my code and the error message you provide does not link back
to the sequence of commands you have used.
- the "ugarchfit" function will not thrown an error starting
"ugarchfilter" (unless you have fixed all the parameters in the
specification which you have not done).
- The error has expected parameters for the ma order ending at 9 which
cannot be the case since you have used 19 in your specification.

What version of rugarch are you using?

-Alexios

On 25/11/2013 14:41, tvernay wrote:
> Deal all,
> 
> Using the ugarchfit function from the (very good) rugarch package with a
> given external regressor matrix archxreg (3 columns), I got a strange error
> that I do not understand. The following code:
> 
> ###
> archspec <- ugarchspec(
> mean.model   
> =list(armaOrder=c(18,19),external.regressors=archxreg,archex=FALSE),
> variance.model=list(garchOrder=c(2,2),external.regressors=NULL),
> distribution="std");
> #
> ctrl = list(RHO = 1,DELTA = 1e-8,MAJIT = 100,MINIT = 650,TOL = 1e-6);
> #
> myarch      <- ugarchfit(archspec,NCO,solver = "solnp",solver.control =
> ctrl)
> ###
> 
> provides the following error:
> 
> ---
> ugarchfilter-->error: parameters names do not match specification
> Expected Parameters are: mu ar1 ar2 ar3 ar4 ar5 ar6 ar7 ar8 ar9 ar10 ar11
> ar12 ar13 ar14 ar15 ar16 ar17 ar18 ma1 ma2 ma3 ma4 ma5 ma6 ma7 ma8 ma9
> mxreg1 mxreg2 mxreg3 omega alpha1 alpha2 beta1 beta2 shape
> ---
> 
> Note that this error does not appear if 'external.regressors=archxreg' is
> replaced by 'external.regressors=NULL', or if some different external
> regressors are considered. Does anyone know where this kind of error may
> come from?
> 
> Many thanks in advance,
> 
> Thibaut
> 
> 
> 
> 
> 
> --
> View this message in context: http://r.789695.n4.nabble.com/rugarch-error-in-ugarchfit-due-to-external-regressors-tp4681114.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.
> 
>