I've run a binary logistic regression analysis, and I’m unsure how to interpret some of the odds-ratios. I tested the predictive capacity of three independent categorical variables on a binary dependent variable, and in one of those categorical variables (one with five categories), all four categories test significant compared to the reference category, and all have odds ratios < 1. The largest of the four odds-ratios is 0.13. May I then conclude that all categories are at least (1-0.13=0.87=) 87% less likely than the reference category to achieve dependent outcome 1? Or doesn't that add up? Thanks in advance for the help!


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.