I am using zero inflated negative binomial models with zinb and using testnl afterwards hoping to test the nonlinear (i.e. logit) portion of the model. How I can make sure that I am actually testing the logit results rather than the linear results when using testnl?
Here's what I have so far:
zinb irinc2 musbn3 minor1 mwhitot2, inf(musbn3 minor1 mwhitot2)
testnl _b[musbn3] = _b[mwhitot2]
I've also tried (and got different results for):
testnl [inflate]_b[musbn3]=[inflate]_b[mwhitot2]
*
* 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/
