[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Melaku Fekadu <firstname.lastname@example.org>
Wed, 21 Mar 2012 11:35:35 +0200
I want to use nnmatch to look for a control group. At this stage, I am
not estimating a treatment effect, because I do not have a measure of
the outcome variable yet. I will do that later on when I will collect
the outcome variable through interview.
In short, I am now interested only in building a control group.
My question is this: in nnmatch the first variable after nnmatch is
the outcome variable (y in the syntax below) which I do not have at
the moment. How can I get rid of this variable, so that the nnmatch
recognize that I do not use an outcome variable? Or are there othet
matching methods that do what I am aiming for?
nnmatch y t x1 x2 [w=w], met(matname) bias(x1 x3) exact(x4) pop
* For searches and help try: