Hi,
I am trying to estimate a standard dynamic probit model with additive unobserved
heterogeneity (random or fixed effect) using unbalanced panel data. I am facing
the usual initial conditions problem: the initial observations of the binary
dependent variable should be allowed to depend on the unobserved heterogeneity.
The method proposed by Wooldridge (2005) is not applicable here because the
panel is unbalanced, and I do not observe the initial conditions for many
individuals in the sample. I should probably also mention that aside from the
state dependence parameter, I need the estimate of the constant, and of the
(relative) variance of the unobserved heterogeneity. Does anyone on the list
know of a way to use Stata to estimate such a model on an unbalanced sample?
Many thanks!
Ivan Vidangos
*
* 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/
