Nonparametric quantile estimation with correlated failure time data
Nonparametric quantile estimation with correlated failure time data
复制标题
DOI：
10.1023/b:lida.0000012422.30514.c7
复制
发表时间：
2003-12-01
影响因子：
1.3
通讯作者：
Kim, J
中科院分区：
文献类型：
--
作者：
Cai, JW;Kim, J
在生物医学研究中，经常出现相关失效时间数据。虽然对具有独立截后故障时间数据的分位数的点估计和置信区间估计已经进行了广泛的研究，但具有相关故障时间数据的分位数估计尚未得到发展。在本文中，我们提出了一种具有相关失效时间数据的分位数的非参数估计方法。我们推导了分位数估计量的渐近性质，并提出了基于自举和核平滑方法的置信区间估计量。仿真研究了所提出的估计器的有限样本特性。最后，我们用中耳炎患者的研究数据集来说明所提出的方法。
In biomedical studies, correlated failure time data arise often. Although point and confidence interval estimation for quantiles with independent censored failure time data have been extensively studied, estimation for quantiles with correlated failure time data has not been developed. In this article, we propose a nonparametric estimation method for quantiles with correlated failure time data. We derive the asymptotic properties of the quantile estimator and propose confidence interval estimators based on the bootstrap and kernel smoothing methods. Simulation studies are carried out to investigate the finite sample properties of the proposed estimators. Finally, we illustrate the proposed method with a data set from a study of patients with otitis media.