Dear Statalisters,
I have cross-sectional time-series data and my dependent variable is a discrete choice variable. I expect that agents' previous choices affect theír current choices. Thus, I would like to include a lagged dependent variable in the model. However, I am not sure what would be the right approach. I know that if the errors are correlated over time, the choice in one period is correlated with the erros in subsequent periods. In addition, I do not observe the first choice sitiuation of the agents and thus I think I face also the so-called initial condition problem.
I would be grateful for any help on how to deal with these problems in Stata. I would also be grateful for any reference dealing with these issues in the setting of discrete choice models.
thank you in advance.
Best reagards,
Laura Vartia
*
* 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/
