cDCC GARCH model in R

Machine Learning and Modeling
,
1

Hello i'm trying to estimate a correlation matrix. The algorithm seems to work, but i have two questions. How do i test it ( do i have to necessarily perform simulations ?) . And i couldn't anderstand what the argument ts in cdcc_estimation is for.

library(rugarch)
library(xdcclarge)
#load data

mydata= read.csv("returns.csv", header=TRUE)
n<-6
mydata=mydata[,c(21,23,55,58,64,66)]


  


# Step 1:GARCH Parameter Estimation with rugarch


spec = ugarchspec()
mspec = multispec( replicate(spec, n = n) )
fitlist = multifit(multispec= mspec, data = mydata)
ht<-sigma(fitlist)^2    # les variances conditionnelles
residuals<-residuals(fitlist)


# Step 2:cDCC-GARCH Parameter Estimation with xdcclarge
cDCC<-cdcc_estimation(ini.para=c(0.05,0.93) ,ht ,residuals,method="NLS", ts=1)
#Time varying correlation matrix Rt at time t
(Rt<-matrix(cDCC$cdcc_Rt,n,n))
2

As for this part, the description for cdcc_estimation() is:

This function estimates the parameters(alpha,beta) and time-varying correlation matrices(Rt) of cDCC-GARCH model.

It returns "time-varying correlations(Rt) and the result of estimation" where "Rt are vectorized values of the conditional correlation matrix(Rt) until time t(ts) for each row."

The argument ts is ts how many time series are you taking(default:1 latest value).

There's a great post on testing statistical code here:

3

This topic was automatically closed 21 days after the last reply. New replies are no longer allowed.