On Sun, 24 Nov 2013, Allin Cottrell wrote:
On Fri, 22 Nov 2013, Pindar wrote:
> when checking whether the coefficients of Poisson FE correspond to those of
> the Poisson model with unitdummies I noticed that when using the poisson
> command without constant only the beta_hat of regressors starting from x2
> on were identical. When using global constant all estimated coefficients
> were identical. [...]
Yes, it appears that the build-in "poisson" command is broken for the
no-constant case. We'll see to that shortly.
It's now fixed in CVS.