03-10-2017 05:52 AM
Here is the issue I am facing :
I have panel dataset and a dependent data that is ordered.
I want to perform a dynamic ordered probit panel model (CARRO, J. TRAFERRI A. (2014) State dependence and heterogeneity in health using a bias corrected fixed effects estimator. Journal of Applied Econometrics, 29, 181-207.) and, as far as I known I have to choose between dynamic (proc panel) and probit (Logistics, probit...).
Would you know a way to mix both approaches ?
We do thank you,