Thanks Mike,
I am exactly trying to find a way to make STATA to do the thing you said
below. So far, I couldn't do it.
>You need to create 11 new variables: Xi_1987 - Xi_1997. The value >of Xi_1987 for each year t in your sample should be set to the 1987 >value of Xi. That is, you repeat the 1987 values for the 1988 >observations on Xi_1987, and for the 1989 observations, and for the >1990 observations, and so on. Repeat similarly for Xi_1988 through >Xi_1997. Then run your proposed regression.
Let me give you a brief reasoning. I am actually trying to run a new version of Chamberlain Random Effects Probit Model which was proposed by Wooldridge. Since I am dealing with a dynamic model with lagged dependent variable, I need to resolve the inital conditions problem. Wooldridge (2002) proposes a MLE which solves this problem by including all the history and the future values of the explanatory variables with the contemporary values. You can actually find more detail in Wooldridge's recent panel data book.
Caglar
*
* 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/
