Hello Sven,

Yes I mean all possible combinations of regressors.

​

PG

Periklis Gogas
Associate Professor
of Economic Analysis and International Economics
Department of Economics, Democritus University of Thrace

Associate Editor - Journal of Economic Asymmetries 
Euro Area Business Cycle Network - Fellow
The Rimini Centre for Economic Analysis - Fellow
The Society for Economic Measurement - Member
Institute for Nonlinear Dynamical Inference (INDI) - Charter Fellow

Σύγχρονοι Ελληνικοί Μύθοι - το νέο μου βιβλίο

On Fri, Jun 15, 2018 at 4:50 PM Sven Schreiber <svetosch@gmx.net> wrote:

Am 15.06.2018 um 14:55 schrieb Riccardo (Jack) Lucchetti:

On Fri, 15 Jun 2018, Periklis Gogas wrote:

Are there any variable selection methodologies included in Gretl?
Something like STEPLS, Combinatorial, etc?

The two possibilities that come to my mind atm are the omit command with the --auto option and M. Błażejovski & J. Kwiatkowski's excellent BMA function package (https://www.jstatsoft.org/article/view/v068i05).

Thanks for pointing it out, it wasn't obvious to me before that it can be viewed as a variable selection tool.

Adding more options would make for a very nice function package, IMO.

There is also the 'addlist' function package by Allin which does the specific-to-general direction. (omit --auto being general-to-specific)

With "combinatorial" do you mean trying out all possible specifications by brute force?

cheers,
sven

_______________________________________________
Gretl-users mailing list
Gretl-users@lists.wfu.edu
http://lists.wfu.edu/mailman/listinfo/gretl-users