I am posting this on behalf of a colleague. All replies can be sent to
me at [log in to unmask]
Stephanie MacNeill
Dear All,
Using a conditional logistic regression model (stata7) I am analysing a
case-control data set with 10 exposure groups. I want to generate odds
ratios of each exposure group compared to group 10 as it has the lowest
exposure). The problem is that group 10 does not have any cases, and
therefore I can't generate any meaningful odds ratios. Does anyone have
any suggestions how to solve this problem? I have considered adding 0.5
to each group (which is very difficult to do, maybe impossible, in
Stata, and also may not be statistically sound), and combining group 10
with another group although I would like to avoid this.
|