how to test significance of VAR coefficients in DCC GARCH Fit
I fit a DCC-GARCH model using "dccfit" function in "rmgarch" package. The
"show()" method there gives summary of the GARCH and DCC parameters only,
but not of the VAR ones. May you suggest me how to get the summary
(including significance test) of the VAR parameters please?
Re: how to test significance of VAR coefficients in DCC GARCH Fit
The estimates of the VAR parameters and the Garch parameters are asymptotically independent. Therefore you first fit the VAR parameters are then fit the Garch model on the residuals (if there any Arch Effect at all). Therefore, you can get all asymptotic parameter estimates result from appropriate VAR fitting tool (there are lot of available with R.)
Currently the DCCfit object (returned from running dccfit) does not
return all the information on the VAR (coefficients can be extracted by
looking at the model slot and 'varcoef' list i.e. fit@model$varcoef).
A better approach is to first estimate the VAR model using the function
'varxfit' in the package which returns the standard errors and all
relevant information, and then passing this returned object to the
dccfit routine (example follows).
Data = dji30ret[, 1:3, drop = FALSE]
spec = dccspec(uspec = multispec( replicate(3, uspec) ), VAR = TRUE,
lag = 1, dccOrder = c(1,1), asymmetric = FALSE, distribution = "mvnorm")
fit = dccfit(spec, data = Data, fit.control = list(eval.se=TRUE),
VAR.fit = vfit)
The package also includes for convenience the 'varxfilter',
'varxforecast' and 'varxsim' functions which are used by the
multivariate garch routines internally.
As mentioned in the documentation, a comprehensive list of examples are
included in the 'inst/rmgarch.tests' folder of the package.
On 14/03/2012 16:04, mamush bukana wrote:
> Dear all,
> I fit a DCC-GARCH model using "dccfit" function in "rmgarch" package. The
> "show()" method there gives summary of the GARCH and DCC parameters only,
> but not of the VAR ones. May you suggest me how to get the summary
> (including significance test) of the VAR parameters please?
> Many thanks as usual
> [[alternative HTML version deleted]]
> [hidden email] 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.