A log-rank type test to compare net survival distributions

International audienceIn population-based cancer studies, it is often of interest to compare cancer survival between differentpopulations. However, in such studies the exact causes of death are often unavailable or unreliable. Net survivalmethods were developed to overcome this difficulty. Net survival is the survival that would be observed, in ahypothetical world, if the studied disease were the only possible cause of death. The Pohar-Perme estimator (PPE)is a non-parametric consistent estimator of net survival. In this paper, we present a log-rank-type test for comparingnet survival functions estimated by this estimator between several groups. We expressed our test in the countingprocess framework to introduce the inverse probability weighting procedure as done in the PPE. We built a stratifiedversion to control for categorical covariates affecting the outcome. Simulation studies were performed to evaluate theperformance of our test and an application on real data is provide