st: Constrained optimization in mata

[Benjamin Villena Roldan <benjaminvillena@hotmail.com>]

Dear statalist,
I'm maximizing an unconstrained almost quadratic form function that looks like this
 
max -H*W*H'  where H=H(b)=[h1(b) h2(b) ... hn(b)]  and b is a vector of choice variables
 
I'm doing this task with optimize() in mata. I can do this with no problem
The next thing I need to do is to optimize under the constraint that a certain number of coefficients are zero, i.e. I need to impose b1=0 for b=(b1,b2). Of course, I can rewrite the problem imposing that condition (math is straightforward) but I think it is more practical in this case if I can use some feature of optimize() that allows me to impose that constraint. Any ideas?
 
Thanks
 
Benjamin 		 	   		  
_________________________________________________________________


*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/