Dear listers:
I am aware of previous posts regarding nlcom and use of macros. My
problem is different.
I have included sample output:
regress rpcinc lgini
Source | SS df MS Number of obs
= 2688
-------------+------------------------------ F( 1, 2686) =
5411.08
Model | 8.0104e+10 1 8.0104e+10 Prob > F =
0.0000
Residual | 3.9763e+10 2686 14803795.6 R-squared =
0.6683
-------------+------------------------------ Adj R-squared =
0.6682
Total | 1.1987e+11 2687 44610141.6 Root MSE =
3847.6
------------------------------------------------------------------------------
rpcinc | Coef. Std. Err. t P>|t| [95% Conf.
Interval]
-------------+----------------------------------------------------------------
lgini | 107085 1455.75 73.56 0.000 104230.5
109939.5
_cons | -34119.9 689.5794 -49.48 0.000 -35472.06
-32767.74
------------------------------------------------------------------------------
. nlcom log(lgini)
expression (log(lgini)) evaluates to missing
r(498);
Clearly, the problem is in my usage of nlcom syntax. Is it the case that
nlcom is more stringent than test command? I am familiar with test and
have not had this problem.
Again, I see nothing in the manual/help to steer me, but I know I am
messing something up.
Any help, as always, is appreciated.
Ed
Edward Blackburne
Associate Professor
Economics and International Business
Sam Houston State University
*
* 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/
