Dear Statalist:
When I run dprobit, stata reports P>|z| that corresponds to the test
of the underlying coefficient being 0. However, when I format the
dprobit output using outreg2 (e.g.: outreg2 using myfile, bdec(3) nor2
bracket nocons addstat(Pseudo R-squared, `e(r2_p)')) the significance
levels reported in outreg2 seem to be for the marginal effects, and
not for the underlying coefficients as in the drobit output. Is there
a way to have outreg2 report significance levels corresponding to the
null on the underlying coefficient?
cheers,
sandu
*
* For searches and help try:
* http://www.stata.com/help.cgi?search
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
