Rank-based inference for the accelerated failure time model
Rank-based inference for the accelerated failure time model
复制标题
DOI：
10.1093/biomet/90.2.341
复制
发表时间：
2003-06-01
期刊：
影响因子：
2.7
通讯作者：
Ying, ZL
中科院分区：
文献类型：
--
作者：
Jin, ZZ;Lin, DY;Ying, ZL
针对截尾观测下的半参数加速失效时间模型，提出了一类基于秩的单调估计函数。相应的估计量可以通过线性规划得到，并证明是一致的和渐近正态的。极限协方差矩阵可以通过一种不涉及非参数密度估计或数值导数的恢复技术来估计。新的估计代表了基于熟悉的加权对数秩统计量的非单调估计方程的一致根。仿真研究表明，所提出的方法在实际环境中表现良好。提供了两个真实的例子。
A broad class of rank-based monotone estimating functions is developed for the semi-parametric accelerated failure time model with censored observations. The corresponding estimators can be obtained via linear programming, and are shown to be consistent and asymptotically normal. The limiting covariance matrices can be estimated by a resampling technique, which does not involve nonparametric density estimation or numerical derivatives. The new estimators represent consistent roots of the non-monotone estimating equations based on the familiar weighted log-rank statistics. Simulation studies demonstrate that the proposed methods perform well in practical settings. Two real examples are provided.