Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down on April 23, and its replacement, statalist.org is already up and running.


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

st: clogit with multiple cases


From   "Tomas Lind" <tomas.lind@ki.se>
To   <statalist@hsphsun2.harvard.edu>
Subject   st: clogit with multiple cases
Date   Fri, 5 Mar 2010 11:38:46 +0100

Dear Statalisters,


Model 1 has 52 cases in stratum 1 with exposure 11 and 3 controls with
exposure 8, 9 and 10. Stratum 2 has 63 cases etc.

Model 2 is similar but here I use a weight (to "repeat" each stratum
"weight" number of times).


Conditional logistic regression with -clogit- handles stratum with a
different numbers of cases and controls. However, model 1 below does not
work, bur model 2 works fine. Why? (I am using Stata 10.)


-------------------
 Model 1
-------------------

id   death	  expo
1     52	   11
1      0      8
1      0      9
1      0      10
2     63      14
2      0      8
2      0      4
2      0      11

etc etc (lots of stratum)


clogit death expo , group(id)



--------------------------
Model 2
--------------------------

id   death	  expo   weight
1      1	   11	52
1      0      8	52
1      0      9	52
1      0      10	52
2      1      14	63
2      0      8	63
2      0      4	63
2      0      11	63

etc etc (lots of stratum)


clogit death expo  [fw=weight] , group(id)



/Tomas


*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/


© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index