Dear all,

I am estimating an IV-oprobit using the cmp command. How can I test the validity of my instruments?

I try adding the instrument to the second stage:

cmp (y=x1 x2 x3 z1) (x1= z1 x2 x3 ), ind ($cmp_oprobit $cmp_probit)
y=ordinal dependent variable
x1= dummy variable
z1= instrument dummy variable

(as Roodman suggests in a forum post).
However, I have some questions to ask :

the coefficient of z1 is not statistically significant in the second stage equation, but the coefficient
atanhro_12 is statistically significant

How can I interpret these results? Is the instrument valid or not?



If I have misinterpreted Prof Roodman's advice, I ask for help and clarification.

Thanks.