So I have ordinal data that is marked as strongly agree, agree, neither agree nor disagree, disagree and strongly disagree and two different groups which I am comparing. I have used a mann whitney to see if the groups are significantly different. Now I would like to see if this difference is still significant when adjusting for age, gender and BMI. Do I use ordinal logistic regression to adjust for these covariates?
1 Answer
$\begingroup$
$\endgroup$
4
Yes. When the dependent variable is ordinal, ordinal logistic regression is often appropriate.
answered Jul 15, 2017 at 14:24
-
$\begingroup$ This does not provide an answer to the question. To critique or request clarification from an author, leave a comment below their post. - From Review $\endgroup$ Jul 15, 2017 at 15:10
-
$\begingroup$ The question was whether to use ordinal logistic. The answer is "yes". $\endgroup$ Jul 16, 2017 at 12:50
-
3$\begingroup$ Questions that have purely "yes" or "no" answers typically are considered off-topic on SE, Peter. We can make them on topic by providing more expansive answers than specifically requested. I believe that is the point @kjetil was trying to make. $\endgroup$– whuber ♦Jul 25, 2017 at 14:17
-
3$\begingroup$ OK, but then should this question be deleted? It sure seems like a statistics question, and it also seems like "Yes" is a full answer. $\endgroup$ Jul 26, 2017 at 11:48