On Mon, 30 Apr 2018, Sven Schreiber wrote:
Am 28.04.2018 um 11:29 schrieb Riccardo (Jack) Lucchetti:
> Actually, the new setup has been in git for at least a couple of weeks.
While we're at it, is it expected that the following fails?:
<hansl>
open djclose.gdt
arima 2 0 2 ; djclose # non-finite starting val of objective (or sth)
</hansl>
This is the snapshot April 18th.
It works with --conditional.
Ah, the initializer produces a non-stationary AR polynomial in that
case. I've now (in git) extended Jack's "flipping" mechanism to deal
with that.
Allin