Thanks a lot Artur and Sven. This was very helpful. Another question, I saw in the documentation that the possibility of combining sign restrictions and zero restrictions on the C matrix is still in the works. Is there a way to work around this while a new version of the SVAR addon comes out?

Again thanks!

On Fri, Aug 26, 2022 at 4:20 AM Sven Schreiber <sven.schreiber@fu-berlin.de> wrote:

Am 26.08.2022 um 08:29 schrieb Riccardo (Jack) Lucchetti:

On Fri, 26 Aug 2022, ajgalindo@gmail.com wrote:

Dear all. Its there a way to estimate bayesian VARs with sign restrictions in GRETL? Thanks in advance for any help. Best regards, Arturo.

Yes. It's in the SVAR addon. See secion 8 of the pdf doc.

Let me add to that that currently the VAR itself (the reduced form, so basically the autoregressive coefficients) cannot be estimated with actual shrinkage in the SVAR addon. (No real Bayesian prior imposed on those coefficients there.) That doesn't have to be a problem, I just want to make it transparent.

Some tools to estimate BVARs (in the reduced-form sense, not structural) are in the works by some members of the gretl team, but my guess is that it won't happen before the winter (in the Northern Hemisphere).

cheers

sven

_______________________________________________
Gretl-users mailing list -- gretl-users@gretlml.univpm.it
To unsubscribe send an email to gretl-users-leave@gretlml.univpm.it
Website: https://gretlml.univpm.it/postorius/lists/gretl-users.gretlml.univpm.it/