Re: [Gretl-devel] menus AR(1) / autoregr. / vs. "ordinary" AR
On Tue, 2 May 2017, Allin Cottrell wrote:
I like the idea of a Multivariate submenu, and that's now in git.
Note that
this means the menu attachment for SVAR should be changed for the next
release.
And the same goes for the MGARCH package. I think this will have to be
done after releasing 2017b, though.
But a couple of other thoughts here: might we be better off with two
menus: "Univariate time series" and "Multivariate time series"? As
things
stand we have a pretty deep cascade of Time series/Multivariate/Cointegration
test/Johansen. Or alternatively,
move the two cointegration options up a level?
Cointegration test (Johansen)
Cointegration test (Engle-Granger)
I quite like the menu structure that's now in git.
As for "AR(1)" and "Autoregressive estimation", I
agree they want cleaning up
in some way but I'm not sure yet what's best. I'm not so keen on parking them
under "Other linear models" because they are time-series specific. Maybe a
single entry "AR errors (GLS)" with a fork to first-order vs general?
I guess it's a matter of perceived relative importance. By stretching your
argument only a little, one could argue that dpanel could live in the time
series menu because the model that gets estimated is inherently dynamic
and the fact that data are longitudinal is just a minor detail. I
personally tend to view GLS estimators as a clever old-school solution to
the problem of estmating a model in which the time-series characteristics
are incidental, since what you really care about are the regression
parameters (in contrast with pure time-series models, where in general the
parameters don't have a direct economic interpretation, but are
by-products to some further action, eg forecasting). But it's not vitally
important IMO.
While we're at it, I'm not sure we need the trailing
"..." on lots of the
model menu items (though trashing the ellipses would make some work for
translators).
True. Let's get rid of them.
-------------------------------------------------------
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
-------------------------------------------------------