st: dummy variable question

[Rajesh Tharyan <R.Tharyan@exeter.ac.uk>]

hi all,

I am looking to analyse the impact of indivuduals belonging to class 
(A&B), type (X&Y)  and action (a&b) on a certain effect (Y - a continous 
numeric variable)
i.e
1.  how is effect affected by class the indivudual belongs to - Class A 
or Class B
2.  how is the effect affected by the type of the individual - Type A or 
Type B
3.  how is the effect affected by a certain action-Action a or Action b
4.  how it changes for individuals of a certain class, type
and
5. finally how effect is affected by individuals of a ceratin class and 
type performing a cetain action.

Not sure how to proceed. This is what i have in mind

Do I run 3 seperate regressions for class, type and action on Y with 
dummies for class, type and action (for 1 to 3 above) and then another 
regression with class * type dummy interaction for (4 above) and for 
finally I run a regression with  class* type*action  dummy interaction 
for (5 above).  Is there a better way to analyse this in stata?

regards
rajesh


*
*   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/