Re: [Gretl-users] GARCH Conversion
Am 21.06.2018 um 14:51 schrieb Riccardo (Jack) Lucchetti:
On Thu, 21 Jun 2018, Sven Schreiber wrote:
> Am 21.06.2018 um 12:52 schrieb Periklis Gogas:
>
> It would certainly be interesting whether Eviews gets it right, or
> just gets "something".
Oh, and another thing I just noticed: Eviews' estimate of the ARCH
parameter is 2.44, which makes no sense whatsoever; that parameter
should be bounded between 0 and 1. It appears that the algorithm in
Eviews visits exotic regions of the parameter space and then stops
more or less randomly at some point,
Hehe, and I started worrying that I was prejudiced against Eviews... But
which Eviews version is this anyway?
thanks,
sven