here's another thought for the GUI structural time series modelling options. Currently the Basic Structural Model only has a seasonal cyclical element. Were this to be flexible and allow a user defined periodicity/frequency for annual series, then longer term cycles could be incorporated into the BSM.  Admittedly,  a trig cycle can be added into the exogenous variable group, but it will be deterministic, whereas a stochastic cycle would be useful (as most of those I have looked at are not completely regular).

On Tue, 29 Dec 2020 at 11:05, Sven Schreiber <> wrote:
Am 29.12.2020 um 09:29 schrieb Artur Bala:
> Hi all,
> Ok, this is not such a great topic but I'm going to submit  it anyway...
> In an estimation output, gretl uses the expression "using
> observations...", for example:
> and here "using observations..." loses its meaning given that the actual
> observations  used in the estimation  are not in a row anymore.

I think it's a valid point. If the obs are non-continguous, I guess the
hyphen should be dropped (giving the false impression of a range) and
simply the number of obs given. I'm less sure whether more information
on the precise subsampling should be given in the header, it might
become too large.

Gretl-users mailing list --
To unsubscribe send an email to