Dear Statalisters,
I have an -ivprobit- estimation which contains an interaction term:
ivprobit dvar (var1=var2) var3 var4 var5
where var5 is the interaction term generated from var3*var4
As far as I know, there is no single command to find the interaction
effect and its standard errors for the above in Stata 9.
Doing so by hand, is the interaction effect in this case the same way
as in a simple probit model? That is, differentiating
Normal(_b[_cons]+_b[var1]*var1+_b[var3]*var3+_b[var4]*var4+_b[var5]*var3*var4])
with respect to var3 and then var4. Is this correct?
For the standard errors, will it be correct to run
predictnl interact=<interaction effect>, se(se)
with the se variable giving the standard errors?
I am unsure if my procedure is right, especially since the -ivprobit-
MLE process involves more than one equation.
Would greatly appreciate any comments as well as further suggestions.
Thanks in advance!
Kelvin
*
* 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/
