Improving the efficiency of the log-rank test using auxiliary covariates
Improving the efficiency of the log-rank test using auxiliary covariates
复制标题
DOI：
10.1093/biomet/asn003
复制
发表时间：
2008-09-01
期刊：
影响因子：
2.7
通讯作者：
Tsiatis, Anastasios A.
中科院分区：
文献类型：
--
作者：
Lu, Xiaomin;Tsiatis, Anastasios A.
在比例风险假设下，对数秩检验是检验零假设H-0：beta = 0的最佳方法，其中beta表示风险比的对数。然而，如果有额外的协变量与生存时间相关，利用它们的信息将提高对数秩检验的效率。我们应用半参数的理论来刻画一类经常和渐近线性估计β时，辅助协变量纳入模型，并推导出更有效的估计。这些估计量引起的Wald检验比对数秩检验更强大。仿真研究被用来说明效率的提高。
Under the assumption of proportional hazards, the log-rank test is optimal for testing the null hypothesis H-0 : beta = 0, where beta denotes the logarithm of the hazard ratio. However, if there are additional covariates that correlate with survival times, making use of their information will increase the efficiency of the log-rank test. We apply the theory of semiparametrics to characterize a class of regular and asymptotically linear estimators for beta when auxiliary covariates are incorporated into the model, and derive estimators that are more efficient. The Wald tests induced by these estimators are shown to be more powerful than the log-rank test. Simulation studies are used to illustrate the gains in efficiency.