Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
st: RE: logit for case control
From
Kieran McCaul <[email protected]>
To
"[email protected]" <[email protected]>
Subject
st: RE: logit for case control
Date
Fri, 14 Dec 2012 14:05:20 +0800
...
-logit- and -logistic- are the same regression method. The only difference between them is that -logit- gives beta coefficients by default and -logistic- gives odds ratios by default.
If you have frequency matched the controls to the cases, then you will need a categorical age variable that defines the age strata used and this will need to be in the model as well.
-----Original Message-----
From: [email protected] [mailto:[email protected]] On Behalf Of Sacamano, Paul L.
Sent: Friday, 14 December 2012 5:05 AM
To: [email protected]
Subject: st: logit for case control
Hello,
I've been using logit for a case control database, but not sure this is the most appropriate analysis to run.
The controls were loosely matched (not paired) by age frequency distribution.
The outcome is binary: 30-day hospital readmission (case) or no (control).
The independent variables are categorical (race, insurance, admission diagnosis, etc.) and continuous (age, number of clinic visits, etc.) and dichotomous (yes or no for HCV, CKD, etc.).
Here's an example of what I've been using:
. logit case admgroup sex insurance zip race
and . logistic case admgroup sex insurance zip race
Does this seem to be the correct approach?
Thanks so much.
Paul
*
* For searches and help try:
* http://www.stata.com/help.cgi?search
* http://www.stata.com/support/faqs/resources/statalist-faq/
* http://www.ats.ucla.edu/stat/stata/
*
* For searches and help try:
* http://www.stata.com/help.cgi?search
* http://www.stata.com/support/faqs/resources/statalist-faq/
* http://www.ats.ucla.edu/stat/stata/