st: incorporating spatial lags in a treatment regression Stata12

[julia marasteanu <juliamarasteanu@gmail.com>]

Hi Statalist members,

I am using Stata 12 to run a treatment regression with an endogenous
treatment (treatreg command).  I know that I can incorporate a spatial
lag on the dependent variable by simply using the spwmatrix to create
the weighting matrix, and splagvar to create the lagged variable, but
I am not sure how including this spatially lagged dependent variable
in the RHS affects the post estimation features.  Does anybody have
any suggestions as to how to calculate the average treatment effect
(ATE) or average treatment effect on the treated (ATET) after running
a treatment regression that includes a spatially lagged dependent
variable on the RHS?  Can I simply use the margins command as is, or
do I have to make some changes?

Thank you,
Julia

P.S.  While I have used STATA a good bit, I have only stuck to already
written commands - I am pretty unfamiliar with the programming.
*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/faqs/resources/statalist-faq/
*   http://www.ats.ucla.edu/stat/stata/