Svend appears to have solved the problem, but
I've seen no command on the story that there
was, but now longer is, a -match- command.
I really doubt this, and suspect some confusion
here. It would be most unusual for
an official command to be withdrawn, but
not replaced. It has happened (anyone remind
Stata's idiosyncratic -menu- command?) but
only very rarely.
Nick
[email protected]
Svend Juul
> Kristien Verheyen wrote
> In a case-control study with 1-1 matched pairs and binary
> exposure, how
> do I produce a 2x2 table that shows the number of pairs where (case
> exposed, control exposed); (case exposed, control unexposed); (case
> unexposed, control exposed) and (case unexposed, control unexposed)?
>
> Older versions of Stata had the 'match' command to do this, which
> doesn't seem to exist anymore.
> 'mcc' does not do the trick.
> ------------------------------------------------------------
>
> -mcc- does the trick, but the data must be in wide form, with the case
> and its matched control in the same observation, and that may
> require a
> -reshape-. Try this:
>
> clear
> webuse lowbirth.dta
> keep pairid low smoke
> reshape wide smoke , i(pairid) j(low)
> tab2 smoke1 smoke0
> mcc smoke1 smoke0
>
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
