Sounds like "Deviation contrast". This, and a variety of different means of
coding are available in -xi2- and -desmat- packages.
Stephen McDonald
-----Original Message-----
From: [email protected]
[mailto:[email protected]]On Behalf Of Sarrazin, Mary
Sent: Thursday, 6 February 2003 6:03 AM
To: '[email protected]'
Subject: st: effect coding in STATA
I need to run a logistic regression on some mortality data, but need to
obtain odds ratios that are based on "effect" coding, rather than the
traditional "reference" coding. I generally use SAS, in which it is easy to
request effect coding (so that odds ratios reflect the odds of dying
compared to the "average" patient, rather than compared to some reference
category), but would rather perform this analyses using STATA if possible.
I have searched through the STATA documentation and can't find any mention
of this coding. Is there a way to do this in STATA?
Thanks,
Mary Sarrazin
*
* 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/
