El 26/03/12 10:10, Daniel Bencik escribió:
Hello everybody,
first off, thank you all for suggestions.
Riccardo, I know that anything bigger than arma(2,1) is going to be a
crappy model. Im forecating volatility and arma is one of the options,
the obviously sloppy one but nevertheless the benchmark and I can prove
nowehere else than on out of sample that its great fit is just an
illusion. That's actually the point...
So, the ARMA(6,5)-GARCH(1,1) model with T-distributed residuals in
Eviews gives estimates which are to be seen at
http://eubie.sweb.cz/gretl_forum/Eviews_estimation.PNG
I would say this is showing common roots in the AR and MA parts:
The AR roots 0.59+-0.76i are very close to the MA roots 0.60+-0.77i and
the AR roots -0.79+-0.56i are very close to the MA roots -0.78+-0.58i
So I think this is an ARMA(2,1)-GARCH(1,1)
When I plug in the very same numbers as initial values into my gretl
code, I get convergence, however, I arrive at different estimates, see
http://eubie.sweb.cz/gretl_forum/gretl_forum_correct_starting_values.txt
Yes, this seems to be very different. I cannot see now what the problem
may be, but if you try with the ARMA(2,1)-GARCH(1,1) I am sure it will
be easier to detect the problem.
--
Ignacio Diaz-Emparanza
DEPARTAMENTO DE ECONOMÍA APLICADA III (ECONOMETRÍA Y ESTADÍSTICA)
UPV/EHU Avda. Lehendakari Aguirre, 83 | 48015 BILBAO
T.: +34 946013732 | F.: +34 946013754
www.ea3.ehu.es