Dear Statalisters,
I have a longitudinal data on firms and my dependent variable is a discrete choice variable with three alternatives. I am estimating multinomial logit model with random intercept and would like to analyze state dependence in this setting since I expect that the past values of the dependent variable may affect the current choice. I would like to ask whether it is possible to just include a lagged dependent variable in the regression? Or do I need to consider initial conditions?
I would be grateful for any advice in this question.
Thank you in advance.
Best regards,
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/
