SIMEX method for censored quantile regression with measurement error
SIMEX method for censored quantile regression with measurement error
复制标题
具有测量误差的截尾分位数回归的 SIMEX 方法
DOI：
10.1080/03610918.2016.1242731
复制
发表时间：
2017-01-01
影响因子：
0.9
通讯作者：
Liu, Yanyan
中科院分区：
文献类型：
--
作者：
Mao, Guangcai;Wei, Yi;Liu, Yanyan
审查的分位数回归是生存分析中COX比例危害模型的重要补充。除了受到审查外，一些协变量还可能遇到测量误差。这导致了实质上有偏见的估计，而无需考虑此错误。 SI突变驱除（SIMEX）方法是处理测量误差问题的有效工具。我们将SIMEX方法扩展到审查的分位数回归，并使用协变量测量误差。通过广泛的模拟评估该算法。分析了一项肺癌研究，以验证该方法的验证。
Censored quantile regression serves as an important supplement to the Cox proportional hazards model in survival analysis. In addition to being exposed to censoring, some covariates may subject to measurement error. This leads to substantially biased estimate without taking this error into account. The SI Mutation-Extrapolation (SIMEX) method is an effective tool to handle the measurement error issue. We extend the SIMEX approach to the censored quantile regression with covariate measurement error. The algorithm is assessed via extensive simulations. A lung cancer study is analyzed to verify the validation of the proposed method.