Re: [Gretl-devel] [Gretl-users] multivariate lrvar?
Am 16.04.2018 um 17:52 schrieb Riccardo (Jack) Lucchetti:
On Mon, 16 Apr 2018, Sven Schreiber wrote:
> I mean, either the factor is right or it's wrong, it cannot
be
> "unnecessary" unless the omission is balanced by something else.
Ah, I think I get it now.
If I understand your point correctly, the \hat{Sigma} matrix shown in
the unnumbered equation right after the sentence "Rather, one computes
the sandwich filling by summation as" should be mutlipied by $T$.
Is that right?
Yes, either multiply the RHS of that equation through by T, so that the
definition of \hat{Sigma} becomes something else, or multiply Sigma
itself by T everywhere.
-s