Re: st: generating matched set ID's after PSMATCH2

[Santosh Kumar <santosh.uh@gmail.com>]

Hi all,

Thanks for the response the this query. I wonder if we can generate
similar matched id with Kernel matching.

Thanks,


On Sun, Sep 19, 2010 at 1:18 PM, Ariel Linden, DrPH
<ariel.linden@gmail.com> wrote:
> Hi All,
>
> Perhaps someone has some code to generate IDs of matched sets after running
> the user written program PSMATCH2?
>
> More specifically, I'd like to generate grouped matches with an ID for all
> matches within that set. So if there were 4 controls matched to 1 case, that
> particular group should have a count of 5, and the same group ID should show
> up 5 times. If 1 control was matched to 1 case, there should be two
> individuals with the same group ID.
>
> Thus, the final outcome would be to have a variable (called groupID)with a
> sequential list of IDs (Starting at 1)representing all those cases and
> controls within that matched set. In the example below (assuming 1 to 1
> matching), tx = treatment, _id = the subject ID, _n1 = matched control ID,
> and groupID is the id of both matched case and control. As you can see,
> there are two of each groupID.
>
> Tx      _id     _n1     groupID
> 1       1       6       1
> 1       2       7       2
> 1       3       8       3
> 1       4       9       4
> 1       5       10      5
> 0       6       .       1
> 0       7       .       2
> 0       8       .       3
> 0       9       .       4
> 0       10      .       5
>
> Thanks in advance!
>
> Ariel
>
> *
> *   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/
>



-- 

Santosh

*
*   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/