At least two user-written commands may be of interest to you: -xi3- and
-desmat-. Both are on SSC.
Lee Sieswerda, Epidemiologist
Thunder Bay District Health Unit
[email protected]
-----Original Message-----
From: [email protected] [mailto:[email protected]]
Sent: Monday, July 21, 2003 3:40 PM
To: [email protected]
Subject: st: creating a referent strata for a categorical variable
Greetings Statalisters -
If I have a categorical variable where the values do not assume
any sort of natural ordering (i.e. nominal) and I'd like to use
that variable in a regression analysis (e.g. logistic) with one
value of the variable serving as the referent - how best to
achieve?? If I use the - xi: - command, I obtain a series of
dichotomous variables useful in examining the effect that value
has relative to all others within that variable, but not
necessarily relative to my arbitrary referent group. I
recognize that I could create a series of dichotomous variables
using the -gen- command, but it seems there may be an
alternative way. Any input is appreciated.
Thanks,
Clint Thompson
*
* 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/
