st: Heckman-type selection and cmp

[Chris Smith <cjsmith79@hotmail.co.uk>]

Dear all,
I wish to run a panel data Heckman-type correction model in which the selection equation would be multinomial probit and the outcome equation is continuous. The selection equation would be run on the full sample and would segment the sample into eight groups (including the zero group). The idea is that a separate outcome equation would be run for each of the seven non-zero groups in the second stage. 
I am aware that cmp is the appropriate command for this type of model but I am struggling to think how best to specify the ind() option for the outcome equation. I need to tell cmp to run a separate continuous regression for each of the seven non-zero groups that result from the selection model. I suspect that simply specifying $cmp_cont would result in all non-zero groups being lumped together but I may be wrong. If I am correct, does anyone have any ideas about how I might specify the ind() option?
For completeness, the type of model that I wish to run is below and the element of the model that I am uncertain about is indicated by ???.
cmp (FirmPerf = Xs || firm_ID: ) (OUTCOME_GROUP = Xs || firm_ID: ), ind(???*$cmp_cont $cmp_mprobit) redraws (#)
Many thanks,
Chris 		 	   		  
*
*   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/