I just ran the example script BAYES_DFM.m from Koop (http://personal.strath.ac.uk/gary.koop/Factor_Models.zip) using Octave (latest version 3.6.3 on ubuntu) and it seems to work.
Additionally, I ran a script provided by Veredas/Luciani which one can find here:
http://www.ecares.org/ecare/personal/veredas$/Welcome_files/LucianiVeredas2011_MatlabCodes.zip
To run it on Octave one needs to install the package "signal" for octave and change the line "[Fhat0,eigval]=svd(w*y'*y);" in the file "ML_nfactors.m" to "[Fhat0,eigval,test]=svd (w*y'*y);" where test holds the third scalar.
It also seems to run up to a point and produces some results and a figure, but further adjustment for Octave seems to be needed.
But overall it seems that one can you these mentioned packages with Octave and/or gretl using the foreign-block.
I will experiment a bit with it. If I find some further information, I'll let you know.
Artur
On Fri, 21 Sep 2012, artur tarassow wrote:I'm quite interested in this, although I'm very severely time-constrained in this period. If you could share with me (and publicly on the mailing list if you want) your work I'd be very grateful.
Thank you for this hint, Peter. I'll have a look on their code.
--------------------------------------------------
Riccardo (Jack) Lucchetti
Dipartimento di Economia
Università Politecnica delle Marche
(formerly known as Università di Ancona)
r.lucchetti@univpm.it
http://www2.econ.univpm.it/servizi/hpp/lucchetti
--------------------------------------------------
_______________________________________________
Gretl-users mailing list
Gretl-users@lists.wfu.edu
http://lists.wfu.edu/mailman/listinfo/gretl-users