st: IV estimates splining the endogenous variable in the second stage?

["Andrea Molinari" <A.Molinari@sussex.ac.uk>]

Dear Statalisters,

I am estimating an unbalanced pooled OLS for 420 (pairs of) countries over 
22 years.  There is (at least) one variable that I found to be endogenous 
(and found 'good' instruments for). The problem I've got is that I also 
believe that this variable has two splines (following theory and also when 
observing the data).

Does anyone know, within the -ivreg2-  command, whether and how can I tell 
Stata to use the splinned predictions (instead of the predictions of the 
variable) of this endogenous variable for the second stage?

Any help or comments would be more that welcomed!!!

Andrea 

*
*   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/