If you want to adjust for a categorical variable using -tabodds-:
. tabodds low agecat, adjust(smoke)
The chi-square value for the score test here is .51, p=.475.
And the logistic regression command,
. logit low agecat smoke
The z-value for agecat is -.72, when squared equals .52. Thus further
adjustment for additional variables, either categorical or continuous,
may provide an assessment of trend, adjusting for other variables. The
difference in the tests and the p-values is largely due to the different
methods use to estimate the parameters in the two approaches.
You should be cautious, though, in interpreting the odds ratios for the
trend variable. The coefficients assume that the logit is linear over
the levels of the independent variable (i.e., the same assumption
implicit in the trend test) and the value of the coefficients and the
p-values do depend on the scale.
-p
______________________________
Paul F. Visintainer, PhD
Professor and Program Director
Health Quantitative Sciences
School of Public Health
New York Medical College
-----Original Message-----
From: [email protected]
[mailto:[email protected]] On Behalf Of
[email protected]
Sent: Monday, June 06, 2005 5:16 AM
To: [email protected]
Subject: st: test for trend
Dear all,
Can anyone tell me how I can do a test for trend for an adjusted odds
ratio
estimate derived from a logistic regression? I am interested in
exploring
whether there is an increasing effect on income on my outcome variable
after I
control for all other variables in the model.
Thanks in advance.
Manuela
Manuela De Allegri
University of Heidelberg
Germany
*
* 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/
