Courses / Activities

Weighted Log Rank Tests

66
reads

Wei-Yann Tsai

2010-06-18
12:30:00 - 14:30:00

405 , Mathematics Research Center Building (ori. New Math. Bldg.)



Lecture 2:

When there are two groups, group 1 and group 2, one of the interested question of survival analysis is that whether the survival experience of the 2 groups are equal to each other. Let S1(t) and S2(t) be the survival functions of the 2 groups respectively. Thus, one wants to know whether H0 : S1(t) = S2(t) for all t or Ha : S1(t) <> S2(t) for some t. We will first introduce Gehan’s test which is a generalization of Wilcoxon Rank Sum test. Gehan’s test will be extended to Log Rank Test. The two tests will then be generalized to weighted log rank tests which are also linear rank tests.

Reading:

1. Gehan, E.A. (1965). A Generalized Wilcoxon Test for Comparing Arbitrarily Singly-Censored Samples. Biometrika 52, 203-223. (Primary reading)

2. R Peto, J Peto (1972). Asymptotically efficient rank invariant test procedures. J. Roy. Statist. Soc. (A), 185-207. (secondary reading)

3. RL Prentice (1978). Linear rank tests with right censored data. Biometrika, 167-179. (secondary reading)