Hello respected members, I need your help to forecast portfolio VaR for 3 assets(returns) with the help of DCC Garch model in R. I have done the following steps as you can see from my codes also,
fitting the DCC Garch model with the normal distribution.
generated a series of correlation and covariance matrix named by cor1 and cov1 respectively.
I also generated a forecast series of Correlation and Covariance matrix named by Rf and Hf respectively.
now my question is how can I forecast portfolio VaR?
kindly guide me about the next steps, I shall be very thankful for your precious answers as I am tired after searching different webpages.
my codes in R studio are given below,
getSymbols("IBM", from = startDate,to=endDate)
getSymbols("GOOG", from =startDate, to=endDate)
getSymbols("BP", from =startDate, to=endDate)
uspec.n=multispec(replicate(3,ugarchspec(mean.model = list(armaOrder=c(1,0)))))
spec1=dccspec(uspec = uspec.n, dccOrder = c(1,1),distribution = 'mvnorm')
fit1=dccfit(spec1,data = rx, fit.control = list(eval.se=TRUE),fit = multf)
cov1 = rcov(fit1)
cor1 = rcor(fit1)
dccf1 <- dccforecast(fit1, n.ahead = 10)
Rf <- dccf1@mforecast$R