[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]
st: logistic, dummies: some observations not used, why, and how to change?
somehow my message didn't get through, sorry if you get it double now...
I think this should be anywhere in the manuals, but I can't find it,
probably since I don't know where to search, so maybe you can help?
I use Stata 8.0 SE.
I want to do a logistic regression, with outcome variable CLPL (which can be
0 or 1), and predictor variables EXPOSE (0 or 1) and ORIGIN (10 possible
values, so I created dummies, named _DORnameofcountryorregion).
Here is some output:
. logistic CLPL EXPOSE
Logistic regression Number of obs = 299
LR chi2(1) = 1.02
Prob > chi2 = 0.3118
Log likelihood = -147.99309 Pseudo R2 = 0.0034
. logistic CLPL _DOR*
note: _DOR_latamerica != 0 predicts failure perfectly
_DOR_latamerica dropped and 8 obs not used
Logistic regression Number of obs = 291
LR chi2(5) = 9.35
Prob > chi2 = 0.0958
Log likelihood = -142.04343 Pseudo R2 = 0.0319
My question is: yes indeed, all 8 records on latin america do have CLPL==0,
but I do want to include those observations when I estimate the effect of
ORIGIN on my outcome (as such or in combination with EXPOSE or other
variables). Why does Stata exclude these observations, and what should I do
Thanks for any advice,
* For searches and help try: