[Gretl-devel] Re: bug with fcast
On Mon, 3 Jan 2022, Riccardo (Jack) Lucchetti wrote:
Hi all (and happy new year),
I just found that we have a bug when forecasting from a VECM with exogeneity
restrictions (only with certain options for the deterministic part).
Some more on this: it seems that in the failing cases we don't transcribe
correctly the matrix (internally called B) that corresponds to the "coeff"
element of the returned "system" bundle, although the $coeff accessor
works ok. For example:
<hansl>
open sw_ch14.gdt
infl = 100 * sdiff(log(PUNEW))
vecm 2 1 infl LHUR --crt --quiet
restrict --full
b[1,1] = 1
a[1,1] = 0
end restrict
eval $coeff
eval $system.coeff
</hansl>
returns
<output>
? eval $coeff
-0.00081327 0.14284
0.43167 0.053219
-0.58767 0.58294
0.0000 0.028741
? eval $system.coeff
-0.00081327 0.14284
0.43167 0.053219
-0.58767 0.58294
</output>
-------------------------------------------------------
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
-------------------------------------------------------