[R-SIG-Finance] Multivariate GARCH

Brian G. Peterson brian at braverock.com
Thu Dec 9 15:57:09 CET 2010

On 12/08/2010 08:39 PM, Charles Evans wrote:
> Currently, I am working on an analysis of ETF premiums.  I have
> estimated ECMs for my sample, but the error terms exhibit ARCH behavior.
> Is there a more straightforward way to estimate a multivariate GARCH
> model than mgarch or mgarchBEKK? I have searched for a usable tutorial,
> and I have been unable to find any other than Jeff Ryan's post from 2007:
> https://stat.ethz.ch/pipermail/r-sig-finance/2007q4/001833.html
> and Ruey Tsay's transcript at:
> http://faculty.chicagobooth.edu/ruey.tsay/teaching/bs41202/sp2010/fGarch.txt
> Can anyone direct me to a tutorial that lays out how one estimates a
> multivariate GARCH model in R? I'm not asking for a lesson in basic
> econometrics, just an R-related URL that a researcher in a hurry can use.


mgarch, mgarchBekk, and ccgarch can all estimate multivariate GARCH 
models.  To the best of my knowledge, fGarch cannot.


   - Brian

Brian G. Peterson
Ph: 773-459-4973
IM: bgpbraverock

More information about the R-SIG-Finance mailing list