Abstract
The proportional cause-specific hazards (CSHs) model and the proportional subdistribution (cumulative incidence function (CIF)) hazards model are widely used in competing risk analysis. In this paper, we prove that these two kinds of proportionalities cannot hold simultaneously for all CSH functions and all CIFs.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have