Statalist The Stata Listserver


[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: Help in interpreting Conditional logistic regression output.


From   "Donald Spady" <dspady@ualberta.ca>
To   <statalist@hsphsun2.harvard.edu>
Subject   st: Help in interpreting Conditional logistic regression output.
Date   Tue, 6 Feb 2007 14:15:43 -0700

I have a problem with clogit in that I have paired my "group" variable (age)
as either very tightly paired (same month: variable 'tight) or more loosely
paired (up to 3 months difference: variable "loose).

If I use the same cases I get different odds ratios.
e.g.  If I use as my pairing variable the group "loose" I get the following.

  clogit patient irondef , group(loose) or
note: 112 groups (112 obs) dropped due to all positive or
all negative outcomes.

Iteration 0:   log likelihood = -171.10948
Iteration 1:   log likelihood = -171.07971
Iteration 2:   log likelihood = -171.07971

Conditional (fixed-effects) logistic regression   Number of obs   =	502

LR chi2(1)      =	5.80

Prob > chi2     =	0.0160
Log likelihood = -171.07971                     Pseudo R2       =
0.0167


patient  Odds Ratio   Std. Err.      z    P>z     [95% Conf.	Interval]

irondef        1.75   .4145781     2.36   0.018     1.099985	2.784128

If I use the pairing group "group" I get the following:

  clogit patient irondef, group(tight) or
note: 40 groups (40 obs) dropped due to all positive or
all negative outcomes.

Iteration 0:   log likelihood = -193.28022
Iteration 1:   log likelihood = -190.72021
Iteration 2:   log likelihood = -190.70814
Iteration 3:   log likelihood = -190.70814

Conditional (fixed-effects) logistic regression   Number of obs   =	574

LR chi2(1)      =	16.45

Prob > chi2     =	0.0000
Log likelihood = -190.70814                     Pseudo R2       =
0.0413


patient  Odds Ratio   Std. Err.      z    P>z     [95% Conf.	Interval]

irondef     4.83333   2.167733     3.51   0.000     2.006713	11.64146


In both cases the cases used are the same; they are just grouped slightly
differently.  One equation drops 40 groups and the other drops 112 groups.
The total number of groups is the same for both equations.
My questions are:
1. Is it reasonable to see such a difference in OR between the two
equations?
2. Which is more likely to give the most reliable OR; the equation where the
matching was rigid, or the equation where the matching is more relaxed?

Many thanks in advance.


Donald W Spady MD, MSc
Departments of Pediatrics and Public Health Sciences
8226B, Aberhart Centre 1
University of Alberta
Edmonton, Alberta,
CANADA
T6G 2J3

780-407-1244: Office
780-407-7136: FAX

Nature has no reset button!


*
*   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/



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