DCC Garch model in R goes really long

378 Views Asked by At

I want to estimate DCC GARCH model in R. I have data which contains 340 observation and 10 variables. Those are the logarythimc return rates of my data:

[enter image description here][1]

# univariate normal GARCH(1,1) for each series
garch11.spec = ugarchspec(mean.model = list(armaOrder = c(0,0)), 
                          variance.model = list(garchOrder = c(1,1), 
                                                model = "sGARCH"), 
                          distribution.model = "norm")

# dcc specification - GARCH(1,1) for conditional correlations
dcc.garch11.spec = dccspec(uspec = multispec( replicate(10, garch11.spec) ), 
                           dccOrder = c(1,1), 
                           distribution = "mvnorm")
dcc.garch11.spec


dcc.fit = dccfit(dcc.garch11.spec, data = data)

When I make my code starts, it goes more than few days and doesnt finish. What can I improve or change to get the finished code faster?

1

There are 1 best solutions below

1
On

Faced the same problem)) This is clearly not a problem with the data and the complexity of the model. In my case, two things were done: 1) updating all packages; 2) system reboot. After that, everything worked in a couple of seconds.