Devarajan Karthik, Ebrahimi Nader
Division of Population Science, Fox Chase Cancer Center, Philadelphia, PA 19111.
Commun Stat Theory Methods. 2009 Jan 1;38(14):2333-2347. doi: 10.1080/03610920802536958.
This paper presents methods for testing covariate effect in the Cox proportional hazards Model based on Kullback-Leibler divergence and Renyi's information measure. Renyi's measure is referred to as the information divergence of order γ (γ ≠ 1) between two distributions. In the limiting case γ → 1, Renyi's measure becomes Kullback-Leibler divergence. In our case, the distributions correspond to the baseline and one possibly due to a covariate effect. Our proposed statistics are simple transformations of the parameter vector in the Cox proportional hazards model, and are compared with the Wald, likelihood ratio and Score tests that are widely used in practice. Finally, the methods are illustrated using two real-life data sets.
本文提出了基于库尔贝克-莱布勒散度和雷尼信息度量在Cox比例风险模型中检验协变量效应的方法。雷尼度量被称为两个分布之间阶数为γ（γ≠1）的信息散度。在极限情况γ→1时，雷尼度量变为库尔贝克-莱布勒散度。在我们的案例中，这些分布分别对应基线分布和一个可能因协变量效应产生的分布。我们提出的统计量是Cox比例风险模型中参数向量的简单变换，并与实际中广泛使用的 Wald检验、似然比检验和计分检验进行比较。最后，使用两个实际数据集对这些方法进行了说明。
