Dear All,
I am using balanced panel for the model where the dependent variable is a fraction. Both endogenous and instrumental-variable are binary (0/1). I have read the paper "Panel data methods for fractional response variables with an application to test pass rates," in which the authors considered the endogenous variable as continuous and modeled accordingly. However, in my case, it is not the same. Therefore, I would appreciate advice on expressing the conditional mean model presented in the abovementioned paper (equation 4.1) and how I should estimate the residuals from first-stage regression.

Thank you very much in advance.

Kind regards,
Faruque.