Re: [Gretl-devel] OLS Forecasting
Allin Cottrell schrieb:
Up till now you needed at least 2 equations in a VAR, but in
today's CVS I've enabled single-equation VARs. That's fair
enough, because who said a vector needs >= 2 elements. But this
won't help with cross-referencing levels and differences, which
was the original trigger for this discussion.
I must admit I haven't done much/any forecasting with gretl and I sort
of assumed that forecasting with VARs/VECMs was already all set up and
could be used for this problem.
In any case, in the medium term maybe the open-source code from Jmulti
could be adapted somehow. Now it's still in Gauss, however. Plans to
port it to R have not advanced much, because nobody has found the time
to do it. Actually, given my recent initial exposure to R through
gretl's interface I would like to start working on that eventually,
hoping that the resulting R code could also be beneficial to gretl
(think SVARs for example). But as always, there is so much to do and so
little time...
thanks,
sven