上海财经大学 > 科学研究 > 学术交流 > 学术报告
  • 统计与管理学院2018年学术报告第12期

    【主 题】 Estimating the effect of randomized treatments in the presence of observational secondary treatments

    【报告人】 张敏 副教授

    密歇根大学

    【时 间】 2018年04月11日(星期三)15:00-16:00

    【地 点】 上海财经大学统计与管理学院大楼1208会议室

    摘 要】In randomized clinical trials, for example, on cancer patients, it is not uncommon that patients may voluntarily initiate a secondary treatment post randomization, which needs to be properly adjusted for in estimating the “true” effects of randomized treatments. Whether and when to start the secondary treatment may depend on time-dependent confounders, which is challenging to account for using traditional methods. In this talk, we discuss two causal inference  methods to address this challenge, with one method based on the marginal structural Cox regression model and one method based on dependent censoring. Augmented inverse probability weighted estimators are proposed and evaluated by comprehensive simulation studies.