Thank you all for your comments. I think I have a better handle on the
situation now.
Don Spady
-----Original Message-----
From: [email protected]
[mailto:[email protected]] On Behalf Of Anders
Alexandersson
Sent: February 7, 2007 1:11 PM
To: [email protected]
Subject: Re: st: Interpreting conditional logistic regression equations
using 2 similar types of matching.
Donald Spady <[email protected]> wrote:
> The problem is that if we match loosely on age (within 3 months) as
> opposed to a tight match (1 month) we get different results and I am
> unsure which result is 'best'.
According to Fox News, whatever that means, the report should be "fair
and balanced". More serious, it is fair to report both results. Weigh
more balance (more matching of treatment and control variables)
against the number of observations. Are some observations
theoretically more relevant to your study? More observations are not
always better.
There are several "matching" or "robust" solutions in Stata. I would
also consider the R program MatchIt, see the paper and software at
http://gking.harvard.edu/matchit/.
Anders
[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/
*
* 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/
