Erin wrote:
> I had label values on my dependent variable, so the
> equation names ended up as text strings like
> `"wk ft & pub HI"' `"wk ft & unins"'. Once I dropped
> the value labels, I had equation names like 2 and 3
> and the -keep(eq1:var eq2:var ...)- syntax worked fine.
Erin found another problem with the -keep()- option of
-estimates table-: It cannot be used with equation names
containing spaces. (As far as I know, -mlogit- is the
only estimation command that may produce such equation
names.)
In -estout-, Erin can bring the mlogit labels back in by
adding something like -eqlabels("wk ft & pub HI" ...)-
to her -estout- command.
Furthermore, there should be no problem with the labels
if they do not contain spaces.
ben
*
* 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/
