We study the loss of power of the stratified log-rank test (SLRT) compared to the unstratified log-rank test (ULRT) in the case of\na large number of strata with relatively a small number of stratum sizes in terms of the asymptotic distributions of test statistics\nunder local alternatives. The SLRT tends to lose information due to overstratification. It is better to test the homogeneity among\nstrata before using the stratified log-rank test.
Loading....