Robust estimation and variable selection for the accelerated failure time model.

Robust estimation and variable selection for the accelerated failure time model.
复制标题

DOI:
10.1002/sim.9042
复制
发表时间:
2021-09-10
影响因子:
2
通讯作者:
Wang S
Wang S
中科院分区:
医学3区
文献类型:
--
作者:
Li Y;Liang M;Mao L;Wang S

文献摘要

参考文献

被引文献

相似文献

本文涉及癌症患者生存时间的稳健模型。准确预测患者生存时间对于制定有效的治疗策略至关重要。为此,我们提出了一种与 L1 范数惩罚相结合的统一期望最大化方法,在具有中等大小的右删失生存数据的加速失效时间模型中同时执行变量选择和参数估计。我们的方法适用于一般损失函数,并且当在没有正则化的情况下使用平方误差损失时,可以简化为众所周知的 Buckley-James 方法。为了减轻实际应用中异常值和重尾噪声的影响,我们建议在通用框架下使用鲁棒损失函数。此外,我们的方法可以扩展以合并协变量之间的组结构。我们进行了广泛的模拟研究,以评估所提出的具有不同损失函数的方法的性能,并将其应用于卵巢癌研究作为例证。
This paper concerns robust modeling of the survival time for cancer patients. Accurate prediction of patient survival time is crucial to the development of effective therapeutic strategies. To this goal, we propose a unified Expectation-Maximization approach combined with the L1-norm penalty to perform variable selection and parameter estimation simultaneously in the accelerated failure time model with right-censored survival data of moderate sizes. Our approach accommodates general loss functions, and reduces to the well-known Buckley-James method when the squared-error loss is used without regularization. To mitigate the effects of outliers and heavy-tailed noise in real applications, we recommend the use of robust loss functions under the general framework. Furthermore, our approach can be extended to incorporate group structure among covariates. We conduct extensive simulation studies to assess the performance of the proposed methods with different loss functions and apply them to an ovarian carcinoma study as an illustration.
DOI: 10.1214/14-aos1303
发表时间: 2015-08-01
影响因子: 4.5
作者:
Mai, Qing;Zou, Hui
通讯作者: Zou, Hui
DOI: 10.1214/aos/1176342503
发表时间: 1973-01-01
影响因子: 4.5
作者:
HUBER, PJ
通讯作者: HUBER, PJ
DOI: 10.1097/igc.0000000000000979
发表时间: 2017-06-01
影响因子: 4.8
作者:
Byun, Jung Mi;Jeong, Dae Hoon;Kim, Ki Tae
通讯作者: Kim, Ki Tae
DOI: 10.1080/10618600.2012.681250
发表时间: 2013-06-01
影响因子: 2.4
作者:
Simon, Noah;Friedman, Jerome;Tibshirani, Robert
通讯作者: Tibshirani, Robert
DOI: 10.2307/2281868
发表时间: 1958-01-01
影响因子: 3.7
作者:
KAPLAN, EL;MEIER, P
通讯作者: MEIER, P