Ah, ok, I see: For an AR(2) gretl sets initial values for observations
"-1" and "0", as depicted in the tiny example below. Please correct
me
if I am wrong ;-) But at least using the spreadsheet here confirms this.
Obs Y
----------
-1 # initial value, e.g. = 0
0 # initial value, e.g. = 0
1 # Gretl's official 1st obs. using "-1" and "0"
2 # ....
Artur
Am 11.03.2016 um 07:47 schrieb Riccardo (Jack) Lucchetti:
On Thu, 10 Mar 2016, Artur T. wrote:
> Dear all,
>
> I am playing around (again) with the filter() function.
[...]
> <hansl>
[...]
> # Simulate AR(2) process
> list Ly = y(-1 to -2)
> y = lincomb(Ly,a) + u # 1st version
[...]
> </hansl>
this happens because the list Ly contains two series full of zeros,
which are _not_ updated recursively when you use the lincomb command. If
you append the instruction "eval lincomb(Ly,a)" at the end of your
script, you'll see a series of zeros (with 2 NAs on top).
-------------------------------------------------------
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
-------------------------------------------------------
_______________________________________________
Gretl-users mailing list
Gretl-users(a)lists.wfu.edu
http://lists.wfu.edu/mailman/listinfo/gretl-users