I was wondering if someone knows a way around this: For only one out of 20 heckprobit regressions that I run, Stata does not report the standard error on rho. It does, however, report the chi-square statistics on the null that rho=0 (which happens to be quite small in this particular regression). For other similar regressions, even for one with only one more independent variable (not an instrument) Stata reports rho and its standard error. I have about 200,000 obs. and just 15 variables. Is there something I am doing wrong? The only difference between this and other regressions is that rho is insignificant here. Could it be that the insignificance is due to the failure of estimating a std. error or is it the other way around?
Thanks,
Elda
*
* 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/
