LINEAR RANK-TESTS WITH RIGHT CENSORED DATA
LINEAR RANK-TESTS WITH RIGHT CENSORED DATA
复制标题
DOI：
10.2307/2335292
复制
发表时间：
1978-01-01
期刊：
影响因子：
2.7
通讯作者：
PRENTICE, RL
中科院分区：
文献类型：
--
作者：
PRENTICE, RL
线性秩统计是为检验带有删节数据的回归系数而发展起来的。这些统计是基于广义秩向量的边际概率的分数统计。观察到的Fisher信息通常提供方差估计，而在某些特殊情况下，方差估计的置换方法也是可能的。Wilcoxon检验推广到带有删节数据的回归检验。日志秩检验也是作为一种特殊情况产生的。
Linear rank statistics are developed for tests on regression coefficients with censored data. These statistics arise as score statistics based on the marginal probability of a generalized rank vector. The observed Fisher information provides a variance estimator generally, while in certain special cases a permutation approach to variance estimation is also possible. The Wilcoxon test is generalized to regression tests with censored data. The log rank test is also produced as a special case.