[R-SIG-Finance] RUGARCH - non-negativity constraints on coefficients for exogenous variables in GARCH?

alexios alexios at 4dscape.com
Thu May 21 22:05:46 CEST 2015


1. if the exogenous variables are in the conditional variance equation 
use the "eGARCH" model
2. use setbounds(spec)<-list(vxreg1=c(lower1, 

with lower1, upper1 etc your custom bounds.

If you continue to have problems send me the code/data offlist and I 
will investigate.



On 21/05/2015 20:51, Christian Borelli-Kjær wrote:
> Hi all,
> I am using the RUGARCH package to fit a GARCH model with three exogenous
> variables, but I can only get positive, insignificant parameter estimates
> for the exogenous variables.
> This troubles me, as I have a strong hypothesis that the exogenous
> variables should somehow be "volatility-lowering" - and thus affect the
> conditional volatility in a negative way.
> Does the package constrain coefficients for exogenous variables to be ≥ 0,
> just as alpha and beta, or does it relax this assumption, corresponding to
> e.g. He & Teräsvirta (1997) ?
> Please do request code and data, if needed.
> Thank you for your time,
> Christian Borelli, University of Copenhagen
> 	[[alternative HTML version deleted]]
> _______________________________________________
> 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.

More information about the R-SIG-Finance mailing list