Rank-based variable selection with censored data.

Rank-based variable selection with censored data.
复制标题

DOI:
10.1007/s11222-009-9126-y
复制
发表时间:
2010-04-01
影响因子:
2.2
通讯作者:
Ying Z
Ying Z
中科院分区:
数学2区
文献类型:
--
作者:
Xu J;Leng C;Ying Z

文献摘要

参考文献

被引文献

相似文献

针对半参数加速失效时间模型中惩罚似然(偏似然)方法不能直接应用的情形,提出了一种基于秩的变量选择方法.新方法对基于秩的Gehan型损失函数进行了惩罚,惩罚因子为1。为了正确选择调谐参数,提出了一种新的基于似然的χ2型准则。通过对Gehan损失函数的局部二次展开,得到了估计量的一些性质,如预言性质。特别是,我们的方法可以很容易地实现标准的线性规划软件包,因此数值方便。还考虑了对多变量失效时间边际模型的扩展。通过广泛的模拟研究和两个真实的例子说明了新的程序的性能进行评估。
A rank-based variable selection procedure is developed for the semiparametric accelerated failure time model with censored observations where the penalized likelihood (partial likelihood) method is not directly applicable. The new method penalizes the rank-based Gehan-type loss function with the ℓ1 penalty. To correctly choose the tuning parameters, a novel likelihood-based χ2-type criterion is proposed. Desirable properties of the estimator such as the oracle properties are established through the local quadratic expansion of the Gehan loss function. In particular, our method can be easily implemented by the standard linear programming packages and hence numerically convenient. Extensions to marginal models for multivariate failure time are also considered. The performance of the new procedure is assessed through extensive simulation studies and illustrated with two real examples.
DOI: 10.1093/biomet/asm053
发表时间: 2007-08-01
期刊: BIOMETRIKA
影响因子: 2.7
作者:
Wang, Hansheng;Li, Runze;Tsai, Chih-Ling
通讯作者: Tsai, Chih-Ling
DOI: 10.1093/biomet/88.2.381
发表时间: 2001-06-01
期刊: BIOMETRIKA
影响因子: 2.7
作者:
Jin, ZZ;Ying, ZL;Wei, LJ
通讯作者: Wei, LJ
DOI: 10.1198/016214508000000184
发表时间: 2008-06-01
影响因子: 3.7
作者:
Johnson, Brent A.;Lin, D. Y.;Zeng, Donglin
通讯作者: Zeng, Donglin
DOI: 10.1093/biomet/77.4.845
发表时间: 1990-12-01
期刊: BIOMETRIKA
影响因子: 2.7
作者:
WEI, LJ;YING, Z;LIN, DY
通讯作者: LIN, DY
DOI: 10.1111/j.1467-9469.2005.00487.x
发表时间: 2006-03-01
影响因子: 1
作者:
Jin, Z;Lin, DY;Ying, Z
通讯作者: Ying, Z