[R] Getting forecast values using DCC GARCH fit

Dhivya Narayanasamy dhiv.shreya at gmail.com
Wed Jun 7 06:47:20 CEST 2017


Hi,
I am trying to fit a multivariate time series model using DCC GARCH model
and forecast it.

The data looks like this:

> head(datax)
                    x   vibration_x     Speed
1 2017-05-16 17:53:00      -0.132  421.4189
2 2017-05-16 17:54:00      -0.296 1296.8882
3 2017-05-16 17:55:00      -0.572    0.0000
4 2017-05-16 17:56:00      -0.736 1254.2695
5 2017-05-16 17:57:00       0.000    0.0000
6 2017-05-16 17:58:00       0.000    0.0000

> garch11.spec = ugarchspec(mean.model = list(armaOrder = c(1,1)),
                           variance.model = list(garchOrder = c(1,1),
                                          model = "sGARCH"),
distribution.model = "norm")
> dcc.garch11.spec = dccspec(uspec = multispec( replicate(2, garch11.spec)
),
                  dccOrder = c(1,1), distribution = "mvnorm")
> fit.a = dccfit(dcc.garch11.spec, data = datax[,c(2,3)], out.sample = 500,
                             fit.control = list(eval.se=T))
> dcc.focast=dccforecast(fit.a, n.ahead = 1, n.roll = 499)

May I know how to get the forecast values from 'dcc.focast' ?  I have given
500 as n.roll in rolling forecast. I mean where to find this 500 forecast
values? Any help is much appreciated as I am new to GARCH model.

Also when i plot the forecast model
> plot(dcc.focast, which = 1)

The graph shows weird x axis values starting from 2050 year. Is the graph
showing the forecast values? I have attached the graph as well for your
reference. Thanks in advance.





Regards| Mit freundlichen Grüßen,
> Dhivya Narayanasamy


More information about the R-help mailing list