GRAPHICAL METHODS FOR ASSESSING VIOLATIONS OF THE PROPORTIONAL HAZARDS ASSUMPTION IN COX REGRESSION
GRAPHICAL METHODS FOR ASSESSING VIOLATIONS OF THE PROPORTIONAL HAZARDS ASSUMPTION IN COX REGRESSION
复制标题
DOI：
10.1002/sim.4780141510
复制
发表时间：
1995-08-15
影响因子：
2
通讯作者：
HESS, KR
中科院分区：
文献类型：
--
作者：
HESS, KR
Cox比例风险模型的一个主要假设是，给定协变量的影响不会随着时间的推移而改变。如果这一假设被违反，简单的考克斯模型是无效的，需要更复杂的分析。本文描述了八种检测违反比例风险假设的图形化方法，并在三个已发表的具有单一二进制协变量的数据集上进行了演示。我将讨论这些方法的相对优点。推荐使用比例舍恩菲尔德残差的平滑曲线图来评估PH违规，因为它们提供了关于协变量效应的时间依赖关系的精确有用的信息。
A major assumption of the Cox proportional hazards model is that the effect of a given covariate does not change over time. If this assumption is violated, the simple Cox model is invalid, and more sophisticated analyses are required. This paper describes eight graphical methods for detecting violations of the proportional hazards assumption and demonstrates each on three published datasets with a single binary covariate. I discuss the relative merits of these methods. Smoothed plots of the scaled Schoenfeld residuals are recommended for assessing PH violations because they provide precise usable information about the time dependence of the covariate effects.