The asymptotic properties of nonparametric tests for comparing survival distributions

作者: DAVID SCHOENFELD

DOI: 10.1093/BIOMET/68.1.316

关键词:

摘要: The asymptotic distribution under alternative hypotheses is derived for a class of statistics used to test the equality two survival distributions in presence arbitrary, and possibly unequal, right censoring. include equivalents log rank statistic, modified Wilcoxon statistic invariant procedures introduced by Peto & Peto. When there are equal censoring hazard functions proportional sample size formula F compare exponential samples shown be valid test. In certain situations power falls as amount decreases.

参考文章(11)
B. Efron, The two sample problem with censored data Proc. Fifth Berkely Symp. Math. Statist. Prob.. ,vol. 4, pp. 831- 853 ,(1967)
D. Bernstein, S.W. Lagakos, Sample size and power determination for stratified clinical trials Journal of Statistical Computation and Simulation. ,vol. 8, pp. 65- 73 ,(1978) , 10.1080/00949657808810249
Jaroslav Hájek, Pranab Kumar Sen, Zbyněk Šidák, Theory of rank tests ,(1967)
ROBERT E. TARONE, JAMES WARE, On distribution-free tests for equality of survival distributions Biometrika. ,vol. 64, pp. 156- 160 ,(1977) , 10.1093/BIOMET/64.1.156
Mantel N, Evaluation of survival data and two new rank order statistics arising in its consideration. Cancer chemotherapy reports. ,vol. 50, pp. 163- 170 ,(1966)
Richard Peto, Julian Peto, Asymptotically Efficient Rank Invariant Test Procedures Journal of the Royal Statistical Society: Series A (General). ,vol. 135, pp. 185- 198 ,(1972) , 10.2307/2344317