Community,
I have a quick question that perhaps is easy to solve regarding n.ahead
forecasts.
So for example:
variance_model = list(model = "sGARCH", garchOrder = c(1, 1),
submodel = NULL,
external.regressors = NULL,#as.matrix(Regressors),
#External Regressors will include the news and tweets and market returns
variance.targeting = FALSE)
mean_model = list(armaOrder = c(1,0), include.mean = TRUE, archm = FALSE,
archpow = 1, arfima = FALSE,
external.regressors = as.matrix(Regressors),
archex = FALSE)
distribution_model = "norm"
spec = ugarchspec(mean.model = mean_model, variance.model = variance_model,
distribution = distribution_model)
fit2 = ugarchfit(data = Returns, solver = "gosolnp", spec = spec,out.sample =
66 , DailyVar = f_sigma^2,
solver.control=list(n.restarts=5))
Say now I want to forecast ahead the next two days (66 - intraday data):
forc = ugarchforecast(fit2, n.ahead = 66, n.roll = 0) # Forecasting function
After researching in the documentation and other posts I just have a few doubts:
1 - Because the fit function has a out.sample that = n.ahead forecasts do I
still need to provide the list of external regressors inside the forecast
function?
2 - The >2 n.ahead forecast are calculated using the previous forecast of the
mean and variance equation? I’m assuming yes given what is written in the
documentation but better to confirm.
Thank you for your help,
Eliano
_______________________________________________
[email protected] 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.
