Am 27.11.2018 um 10:37 schrieb Yusuf Abduwahab Hassan:
There is an excellent two page crash course in the documentation of
the SVAR addon package.
I was wondering if Timmy was actually aware of the SVAR addon. I have
repeatedly heard from users who thought gretl could still only deal with
plain Choleski SVARs, and it wasn't quite clear to me from his message
to which part of gretl he was referring to.
In the documentation, it is stated that the SVEC case will receive
own GUI in a future version of the SVAR package however the authors
recommend using the script interface to access the full capabilities
of the SVAR package.
As the second author of the SVAR addon I agree we should try to deliver
on the promise of some GUI wrapping in that area.
On Tue, 27 Nov 2018 at 13:52, Olasehinde Timmy <timmexdareal(a)gmail.com
I am glad to inform you that Gretl is gaining more ground in my
country Nigeria nowadays. However, I will like to make few
suggestions to add to its usefullness.
Thanks, that's good to hear!
I think there is a need to develop a special GUI for SVECM and to
support both long and short run restrictions. If possible, it can
be linked with the VECM output in order to fetched its estimates
from the beta-alpha matrix.
Moreover, I suggest that Gretl should be developed to handle DSGE
Um, that's probably not going to happen any time soon. I'm glad that
also in the DSGE area there is a lot of open-source momentum (keywords
Dynare plus Julia or Python). Gretl doesn't have a comparative advantage
there, so I don't see the reason for making gretl a DSGE tool.
What's more realistic in terms of missing features would be something
like Bayesian VARs which gretl doesn't have, either. (Although
personally I tend to be Bayesian only when I really have a subjective
prior, and often I --and I think the same goes for many others-- don't.
So IMHO another shrinkage/regularization estimator would do just as well.)