Re: [Gretl-users] Features request
On Mon, 25 Apr 2016, Sven Schreiber wrote:
> The first is related to systems: I was wondering whether it would
be
> possible to add the ability to include identities in systems estimated
> with estimators other than FILM; it would be very useful to have such an
> ability for forecasting / simulation purposes, even if estimation is not
> fully efficient; in any case OLS / IV estimation of systems should give
> more robust results.
This is actually directly connected to your next point, because as you say
identities for OLS/IV etc. are only needed for forecasting or simulation, not
for estimation.
>
> A related extension would be to develop a framework to imitate the
> EViews model functionality: add single (estimated or not) equations or
> systems of equations to a bigger model and simulate this structure. I
> understand that this is much more complex from a computational and
> programming point of view than the previous suggestion.
Yes I suggested something like this to Allin and Jack myself some time ago.
There has been some underlying work in gretl's foundations to make this
feasible at some point at the level of Hansl programming/scripting. (For
example making more use of the 'bundle' collection datatype.) However, there
is only so much that Allin and Jack can do.
Note that if forecasting or simulation is done in an extra function package
then the specification of identities would not be necessary in gretl's
'system' estimation command. Instead you would provide the information about
the identitites in the system to the extended forecasting package, and that
package (not yet existing...) might internally call gretl's system
estimation. Of course, it's all a question about the user interface of that
package / add-on.
This is a long-standing issue from Sven's side. Implementing some kind of
interface for handling simultaneous models à la Eviews would be great, and
indeed there are several people apart from Sven who brought this request
up. The problem is, it's really hard. Let's not forget that Eviews
inherited the TSP code, which is probably the BEST implementation of the
econometrics of 1970 (excellent, excellent package).
I would guess that, in theory, one could write a parser in Hansl to handle
systems written in TSP/Eviews syntax within a function package (and thus
take advantage of gretl's own estimation engine). With the level of
sophistication and flexibility that Hansl has now reached this is
definitely possible, but rather time consuming, I would guess. A big
project.
> A third very useful feature in my opinion relates to graphs: it
is very
> useful to have subplots in the same graph, as in matlab / octave.
> graphpg is a substitute with limitations, not least in the number the
> way you put the subplots.
You mean whether it's 2-by-4 or 4-by-2 for example?
Now that we have the "plot" environment, it's not unthinkable that we may
use gnuplot's own multiplot feature in pretty much the same way as we do
with the "scatters" command in a time-series context.
Something like this:
<hansl>
open AWM
gnuplot LNN LNT --time-series --with-lines --output="(a)dotdir/mp1.gp"
gnuplot STN LTN --time-series --with-lines --output="(a)dotdir/mp2.gp"
mpfilename = sprintf("\"%s/mp.gp\"", "@dotdir")
outfile @mpfilename --write --quiet
printf("set multiplot\n")
printf("set size 0.4, 0.4\n")
printf("set origin 0.1, 0.1\n")
printf("load \"%s/mp1.gp\"\n", "@dotdir")
printf("set size 0.4, 0.4\n")
printf("set origin 0.6, 0.6\n")
printf("load \"%s/mp2.gp\"\n", "@dotdir")
printf("unset multiplot\n")
outfile --close
gnuplot --input=@mpfilename --output=display
</hansl>
> A related thing is that it would be nice to have a function to
simply
> estimate the structural factorization. I think that the necessary
> ingredients to do that is the variance covariance matrix form the VAR /
> VECM and a pattern matrix holding restrictions and free elements; could
> you have a public function to do just that, or how is it possible to do
> that in the current state of the SVAR package? I tried to do it myself
> that but the code is so complicated that I gave it up.
Here I don't quite understand what you mean. Once you estimate the SVAR, you
always get the estimated A or B or C. What else do you mean?
I think what Andreas means is a function that returns the estimated
structural matrices given Sigmahat and the contraints. Let me think about
it.
-------------------------------------------------------
Riccardo (Jack) Lucchetti
Dipartimento di Scienze Economiche e Sociali (DiSES)
Università Politecnica delle Marche
(formerly known as Università di Ancona)
r.lucchetti(a)univpm.it
http://www2.econ.univpm.it/servizi/hpp/lucchetti
-------------------------------------------------------