On Mon, 1 Nov 2010, Henrique Andrade wrote:

Dear Developers,

I would like to make a feature request regarding ARCH and GARCH
modelling. Today we can estimate a variance equation like that:

h(t) = a0 + a1*e^2(t-1) + b*h(t-1)

But we can't do this:

h(t) = a0 + a1*e^2(t-1) + b*h(t-1) + c*dummy

I know I could perform this kind of estimation using commercial
econometric packages, but I would like to use Gretl most of the
time (I'm addicted to Gretl :)).

The gig package does that. I need to find some time to release an updated version. Basically, I started the conversion from the "old" gig to a new version which uses bundles internally, but it took much longer than expected and then other priorities took over.

For the moment, you can use the old version. Download the tarball from http://gretl.cvs.sourceforge.net/viewvc/gretl/gretl-addons/gig/?view=tar
and give it a go. Let me know if you need some more info.

Damn, do I need to find some time to work on gig! :-/

Dear Riccardo,

I'm trying the following command (with daily data):

include gig.gfn
list X = const l_crb l_cds l_camb_us l_difjur
list Z = const dummy_iof
matrix results = garchTFit(l_camb,1,1,X,Z)
gig_print(results)

And I'm getting these results: