Variable selection with censored survival data is of great practical importance, and several methods have been proposed for variable selection based on different models. However, the impacts of biased samples caused by left-truncation and covariate measurement error to variable selection are not fully explored. In this paper, we mainly focus on the additive hazards model and analyze variable selection and estimation for survival data subject to left-truncation and measurement error in covariates. We develop the three-stage procedure to correct for error effects, select informative variables, and estimate the parameters of interest simultaneously. Numerical studies are reported to assess the performance of the proposed methods.

具有审查生存数据的变量选择具有重要的现实意义，并且已经提出了几种基于不同模型的变量选择方法。但是，没有充分探讨由左截断和协变量测量误差引起的偏差样本对变量选择的影响。在本文中，我们主要关注累加危害模型，分析存在协变量左截断和测量误差的生存数据的变量选择和估计。我们开发了三个阶段的过程来纠正错误影响，选择信息量大的变量，并同时估计感兴趣的参数。数值研究报告，以评估所提出的方法的性能。