[R] Rugarch issue. Any help would be great!
20282734 at student.uwa.edu.au
Wed Nov 6 06:27:53 CET 2013
I'm having a bit of trouble with my code that I'm writing.
Essentially I'm trying to do a rolling eGARCH forecast for a dataset, namely
DataExplorers which is a portfolio of gold exploration stocks.
I'm hoping to get it so that it calculates the eGARCH for each day and
refits itself each day.
The error message I keep getting is
/"Error in plot.window(...) : need finite 'xlim' values
In addition: Warning messages:
1: In min(x) : no non-missing arguments to min; returning Inf
2: In max(x) : no non-missing arguments to max; returning -Inf
3: In min(x) : no non-missing arguments to min; returning Inf
4: In max(x) : no non-missing arguments to max; returning -Inf"/
I've been googling this issue and trying to adjust the parameters in
ugarchroll. When I do this I get other errors such as
In .makefitmodel(garchmodel = "eGARCH", f = .egarchLLH, T = T, m = m, :
rugarch-->warning: failed to invert hessian"/
In .rollfdensity(spec = spec, data = data, n.ahead = n.ahead,
forecast.length = forecast.length, :
non-converged estimation windows present...resubsmit object with different
Has anyone got an idea whats going wrong? Thanks to anyone who replies, I'm
sure you've got better things to go than answer my questions :)
My code is as follows:
setwd("C:/Users/Scott/Dropbox/Stat 7444 Project/")
goldstockdata = read.csv("DataExplorers.csv", header = TRUE)
t = log(goldstockdata)[1:2500,"Adj.Close"]
goldstockreturns <- diff(log(t))
## Specify GARCH Parameters ##
variance.model = list(model = "eGARCH", garchOrder = c(1, 1)),
mean.model = list(armaOrder = c(1, 1)),
distribution.model = "std"
spec=model, data=goldstockreturns, n.ahead = 1,
n.start = 1, refit.every = 1, refit.window = c("recursive"),
window.size = 1, solver = "hybrid", fit.control = list(),
solver.control = list(), calculate.VaR = FALSE, VaR.alpha = c(0.01,
cluster = NULL, keep.coef = TRUE
str(stockmodelroll at forecast)
stockgarch=stockmodelroll at forecast$density[,"Sigma"]
View this message in context: http://r.789695.n4.nabble.com/Rugarch-issue-Any-help-would-be-great-tp4679841.html
Sent from the R help mailing list archive at Nabble.com.
More information about the R-help