st: using margins to analyze moderation of a quadratic relationship

[Constantin Alba <constantin.alba@gmail.com>]

I am trying to use margins to analyze the moderation of a quadratic relationship

here is the model:

Y = b1 + b2*X + b3*X*X + b4*X*M + b5 *X*X*M

where M is the moderating variable.

to do so I tried to adapt the usage of margins from here
http://www.ats.ucla.edu/stat/stata/faq/conconb11.htm

in the following way:

*///////////////

regress Y c.X##c.M c.X2##c.M
*// X2= X*X

margins, dydx (X X2) at (M=(1 (1) 16))

matrix s=r(b)

margins, at (X=0 X2=0 (M=1 (1) 16)) asbalanced

matrix i=r(b)

*/////////////

question 1: am I doing all correctly up to this point?
question 2: I would like to draw the resulted curves, and cannot
figure the way to do so
question 3. how i change the code to include all other (i.e. control) variables?

thank you in advance

Constantin
*
*   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/