[R-SIG-Finance] garchFit - where are the fitted values for the variance part?
Spencer Graves
spencer.graves at pdf.com
Mon Feb 4 02:47:00 CET 2008
The help page for garchFit says "@h.t : " a numeric vector with the
conditional variances." It says the same thing for "@sigma.t", but
that's clearly a typo: sigma.t = the conditional standard deviation, as
indicated by the following check:
library(FinTS)
library(fGarch)
data(sp500)
spFit30.11 <- garchFit(sp500~arma(3,0)+garch(1,1),
data=sp500)
all.equal(spFit30.11 at h.t, spFit30.11 at sigma.t^2)
TRUE
hope this helps.
spencer
tom soyer wrote:
> Nevermind, I found it... sigma.t instead of fitted. What is h.t??
>
> On 2/3/08, tom soyer <tom.soyer at gmail.com> wrote:
>
>> Hi,
>>
>> I noticed that garchFit provides the fitted mean (i.e., a long repeat of
>> one single value), but it seems there is no fitted values for the variance
>> part. Are they not calculated at all? If so, how could I get the fitted
>> values of the variance? Do I have to manually type the coefficients and
>> write an equation in order to get the fitted values?
>>
>> Thanks,
>>
>> --
>> Tom
>>
>>
>
>
>
>
More information about the R-SIG-Finance
mailing list