st: endogenous variables at different spatial level

[Yu Chen <chenyuffdd@googlemail.com>]

Dear Statalisters,

I 'm estimating two equations at different spatial levels:

 Equation 1: Y=f ( X1, Z, X2)     Y is at postcode level
 Equation 2: Z=f (Y*, X1, X3)    Z is at district level   (district
level is larger than postcode level)

I want to estimate Y at postcode level.
X1, X2, X3 are exogenous variables.
Y* is at district level, equal to the average of Y in a district.
So I think Z should be an endogenous variable which is dependent on
the average of Y .

Could you give me some advice how to estimate these equations? How can
I use 2-stage least squares manually?

Many thanks,
Yu
*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/