Emura Takeshi, Hsu Wei-Chern, Chou Wen-Chi
Biostatistics Center, Kurume University, Kurume, Japan.
Graduate Institute of Statistics, National Central University, Taoyuan, Taiwan.
J Appl Stat. 2021 Oct 21;50(2):264-290. doi: 10.1080/02664763.2021.1990224. eCollection 2023.
A survival tree can classify subjects into different survival prognostic groups. However, when data contains high-dimensional covariates, the two popular classification trees exhibit fatal drawbacks. The logrank tree is unstable and tends to have false nodes; the conditional inference tree is difficult to interpret the adjusted -value for high-dimensional tests. Motivated by these problems, we propose a new survival tree based on the stabilized score tests. We propose a novel matrix-based algorithm in order to tests a number of nodes simultaneously via stabilized score tests. We propose a recursive partitioning algorithm to construct a survival tree and develop our original R package (https://cran.r-project.org/package=uni.survival.tree) for implementation. Simulations are performed to demonstrate the superiority of the proposed method over the existing methods. The lung cancer data analysis demonstrates the usefulness of the proposed method.
生存树可以将研究对象分类到不同的生存预后组中。然而，当数据包含高维协变量时，两种常用的分类树存在致命缺陷。对数秩树不稳定，容易出现虚假节点；条件推断树难以解释高维检验的调整p值。受这些问题的启发，我们提出了一种基于稳定得分检验的新生存树。我们提出了一种新颖的基于矩阵的算法，以便通过稳定得分检验同时检验多个节点。我们提出了一种递归划分算法来构建生存树，并开发了我们自己的R原始包（https://cran.r-project.org/package=uni.survival.tree）用于实现。进行模拟以证明所提出的方法优于现有方法。肺癌数据分析证明了所提出方法的实用性。
