Semiparametric inference for censored data and its applications

在临床试验中，治疗效果的估计依赖于统计模型的一些假设。违反假设可能导致难以解释统计分析结果。在这项研究中，我们提出了一种方法，这是可解释的违反的存在。此外，还需要纳入协变量信息以得出更精确的推断。我们开发了一种方法，有效地利用协变量的信息，以提高统计精度。

In clinical trials, estimation of the treatment effect relies on some assumptions for statistical models. Violation of the assumptions may lead to difficulty to interpret results of the statistical analysis. In this research, we propose a method, which is interpretable in the presence of the violation. In addition, it is desirable to incorporate covariate information to draw more precise inference. We develop a method efficiently utilizing covariate information to increase statistical precision.