Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
From | Nick Cox <njcoxstata@gmail.com> |
To | statalist@hsphsun2.harvard.edu |
Subject | Re: st: How to compose constraint with a series of variables? |
Date | Mon, 21 Mar 2011 09:18:03 +0000 |
Silly comment from me. Was thinking about quite a different problem. Nick On Sun, Mar 20, 2011 at 10:18 AM, Nick Cox <njcoxstata@gmail.com> wrote: > So you don't mind if any of the coefficients is negative? > > Nick > > 2011/3/20 Jorge Eduardo Pérez Pérez <perez.jorge@ur.edu.co>: >> clear >> set obs 1000 >> gen y=uniform() >> forvalues i=1(1)50 { >> gen phrase`i'=uniform() >> gen x`i'=uniform() >> } >> glo sum "" >> local i=1 >> foreach x of varlist phrase* { >> if `i'==1 { >> glo sum "$sum [`x']" >> } >> else { >> glo sum "${sum} + [`x']" >> } >> local i=`i'+1 >> } >> constraint define 1 $sum = 0 >> cnsreg y phrase* x*, constraints(1) >> _______________________ >> Jorge Eduardo Pérez Pérez >> >> >> On Sat, Mar 19, 2011 at 9:20 PM, Muyang Zhang <zmyfudan@gmail.com> wrote: >>> I am only imposing one constraint: the sum of those variables is 0. >>> >>> On Sat, Mar 19, 2011 at 7:43 PM, Nick Cox <njcoxstata@gmail.com> wrote: >>>> You can't, or so I believe. I think the best you can do is to define >>>> many constraints within a loop. For example, suppose you had variables >>>> v1-v1000 and you wanted to impose the same constraint on each. A >>>> skeleton could be >>>> >>>> forval i = 1/1000 { >>>> constraint `i' v`i' = < whatever> >>>> } >>>> >>>> That said, I don't how successful you are likely to be imposing >>>> hundreds of constraints. >>>> >>>> Nick >>>> >>>> On Sat, Mar 19, 2011 at 9:56 PM, Muyang Zhang <zmyfudan@gmail.com> wrote: >>>>> >>>>> I wish to set constraints in regression. I know usually it can be >>>>> implemented by the -constraint- command. >>>>> >>>>> But my problem is that I have a series of variables (over 1000) >>>>> starting with the same phrase followed by numbers. How can I compose >>>>> constraints with -*- operator? > * * 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/