[R-SIG-Finance] Rugarch fitted values lag by 1
Hannah Linder
hlinder33 at gmail.com
Sun Feb 21 05:04:54 CET 2016
Hello,
I am sorry to post a naive question, but I am struggling to sort this out
on my own. I am fitting the following garch model using the rugarch package:
fit.spec1a[[1]]=ugarchspec(variance.model = list(model = "sGARCH",
garchOrder = c(2,0)),
mean.model= list(armaOrder = c(1,0),
include.mean = T),
distribution.model = "sstd")
garch[[1]]<- ugarchfit(data=train.set[[2]][,c(1)],spec =
fit.spec1a[[1]],solver="hybrid")
When I examine the fitted values using fitted(garch[[1]]) the values appear
to lag behind the observed values by 1 even though the length of the fitted
series is equal to that of the observed data (See plot below), so I am not
sure if I am using the fitted function incorrectly, or if the fitted values
are truly lagged. Should be using the fitted values from t=2 until t=T
rather than t=1 until t=T for calculations such as RMSE in-sample.
[image: Inline image 2]
Thank-you very much for any help,
Hannah
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://stat.ethz.ch/pipermail/r-sig-finance/attachments/20160220/71276124/attachment.html>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: image.png
Type: image/png
Size: 46543 bytes
Desc: not available
URL: <https://stat.ethz.ch/pipermail/r-sig-finance/attachments/20160220/71276124/attachment.png>
More information about the R-SIG-Finance
mailing list