Alvine wrote:
As someone create a program to match case and
controls > on 2 or 3 variables ?
and later:
merge is not enough ..I need a program which choose
the best control for each case
--------------------------------------------------------
There was a comment that this was to imprecise, and I agree.
What is the situation?:
1.
You have a pool of potential controls and want to match each
case to one or more controls. You need to obtain more
information from the controls, e.g., by interview.
2.
You have the information needed from the cases and all
potential controls, but want to match for analytic reasons.
In case (2) a matched design and analysis is hardly
justified; just include the potential confounders in a
-logistic- analysis. A matched case-control design requires
a more complex analysis (-clogit-), and it makes it impossible
to study the effect of the matching criteria.
In case (1) a matched design may be reasonable; I don't know,
however, about a program that can do that automatically
for you. One option is to sort the potential controls by the
matching criteria and hand-pick those that give the best match.
(and analyze with -clogit-).
Good luck,
Svend
________________________________________________________
Svend Juul
Institut for Folkesundhed, Afdeling for Epidemiologi
(Institute of Public Health, Department of Epidemiology)
Vennelyst Boulevard 6
DK-8000 Aarhus C, Denmark
Phone, work: +45 8942 6090
Phone, home: +45 8693 7796
Fax: +45 8613 1580
E-mail: [email protected]
_________________________________________________________
*
* 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/
