Am 08.11.2016 um 18:23 schrieb Allin Cottrell:
On Tue, 8 Nov 2016, Sven Schreiber wrote:
> IMO the fix would simply consist of printing out a warning like:
> "Robust s.e. not available for probit random effects estimation, using
> classical variance estimates."
> when a user calls for "probit ... --random-effects --robust".
OK, that's now done in git.
Thanks, and the bug is closed!
In the discussion in that ticket (#202) it became clear that there is
some confusion about the available robust estimation options in
different chapters of the user guide.
But that's really something that a dedicated microeconometrician should
do, eventually...
cheers,
sven