Dear All,
I am going to estimate the following model: Y=a+bX+cX_sqr+dW+error
where X is an endogenous variable and X_sqr is its squared term (X^2) and W is a set of control variables. I have two instuments Z1 and Z2.
Can I estimate the model with this command
or I need to include also Z1 and Z2 squared
?
Thanks for any suggestions or helpful reference.
I am going to estimate the following model: Y=a+bX+cX_sqr+dW+error
where X is an endogenous variable and X_sqr is its squared term (X^2) and W is a set of control variables. I have two instuments Z1 and Z2.
Can I estimate the model with this command
Code:
ivreg2 Y W (X X_sqr=Z1 Z2)
Code:
ivreg2 Y W (X X_sqr=Z1 Z2 Z1_sqr Z2_sqr)
Thanks for any suggestions or helpful reference.
