Abstract
The performances of several linear rank tests for comparing two potentially censored samples is investigated for crossing hazards alternatives. A newly described test (Moreau et al., 1992) which is specifically designed for such alternatives is considered along with the ones most commonly used in survival analysis. Simulations experiments are carried out according to various survival patterns, since survival curves are more used in describing differences between two graphs than hazard functions. In the presence or absence of censoring, power is estimated in situations where survival distributions cross at the beginning, at the middle, at the end and beyond the maximum observed failure time. Simulation results suggest higher power of the Moreau et al. test for medium or late crossing survival curves. This trend is discussed through several examples in oncology.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.