Hello,
I was using garchFit {fGarch} to fit some GARCH processes.
I noticed that the result contains "Log Likelihood" value (right above
"Description"), but when I use @fit$llh to retrieve Log Likelihood value,
the sign switched.
I am confused about which value I should choose to report...
An
Thanks again for the message.
Tried to figure out but failed...
I don't understand how to modify the \psi and combine it to covMest... Sorry
for my poor programming skills.
Can anyone give me some hints?
Thanks a lot!
Ted
David Winsemius wrote:
>
> Look in robustbase; it has a psiFunc class.
Hello,
I have a univariate data set, and the unconditional variance is 1. I would
like to fit a GARCH(1,1) model to the data set with a constraint: \omega
(the constant parameter in GARCH(1,1)) is equal to 1-\alpha-\beta. So the
unconditional variance can be controled to be \omega /(1-\alpha-\
3 matches
Mail list logo