What is your idea?

Is it possible to act as below?

odds ratio = (p2/(1-P2)/(P1/(1-P1)

if: we want risk diff (i.e. P2-P1=P)

then: odds ratio = P/(1-P)

if: having odds ratio from logistic regression

then: P = adjusted attributable risk!

More Seyyed Amir Yasin Ahmadi's questions See All
Similar questions and discussions