Dear Statalisters,
The inflate(_cons) option does not seem to be working with countfit.
Countfit is a user-written command and can be found via -findit countfit- and spost9_ado
If I do
zinb count persons livebait,inf(_cons) nolog
Zero-inflated negative binomial regression Number of obs = 250
Nonzero obs = 108
Zero obs = 142
Inflation model = logit LR chi2(2) = 46.03
Log likelihood = -441.424 Prob > chi2 = 0.0000
------------------------------------------------------------------------------
| Coef. Std. Err. z P>|z| [95% Conf. Interval]
-------------+----------------------------------------------------------------
count |
persons | .7830113 .1187954 6.59 0.000 .5501765 1.015846
livebait | 1.671055 .4435819 3.77 0.000 .80165 2.540459
_cons | -2.495246 .541224 -4.61 0.000 -3.556025 -1.434466
-------------+----------------------------------------------------------------
inflate |
_cons | -1.449553 1.16149 -1.25 0.212 -3.726031 .8269255
-------------+----------------------------------------------------------------
/lnalpha | .992627 .4301444 2.31 0.021 .1495595 1.835695
-------------+----------------------------------------------------------------
alpha | 2.698314 1.160665 1.161323 6.269488
------------------------------------------------------------------------------
If I do
countfit count persons livebait,inf(_cons)
I obtain
variable _cons not found
in option inflate()
r(111);
The help file mentions that
the inflate option is used in the same way as in the zip and zinb commands.
Best wishes, Garry