I ran svymean on a binomial varialbe and got a standard error of zero in a
by() category. Rather than an infinite sample size, the category has just
two observations -- a "0" and a "1" for values. Naturally the two outcomes
test significantly different, p<0.0001, which is obviously incorrect. Is
this explainable? (Output below.)
. svymean daymore2, by(cnty40 ) subpop(yellowdaymore2)
Survey mean estimation
pweight: allpstratwt5 Number of obs =
3369
Strata: newstrat Number of strata =
8
PSU: abtid Number of PSUs =
2948
Subpop.: yellowdaymore2==1 Population size =
641703.91
----------------------------------------------------------------------------
--
Mean Subpop. | Estimate Std. Err. [95% Conf. Interval] Deff
---------------+------------------------------------------------------------
--
daymore2 |
cnty40==0 | .6443059 .0114672 .6218213 .6667905 1.769245
cnty40==1 | .5815394 0 .5815394 .5815394 .
----------------------------------------------------------------------------
--
Arnold H. Levinson, PhD
Associate Scientist
Center for Research Methodology and Biometrics
AMC Cancer Research Center
303.777.8801
fax 303.239.3394
[email protected]
Assistant Professor
Department of Preventive Medicine and Biometrics
University of Colorado School of Medicine
[email protected]
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
