时 间：2023年6月2日（周五）15：00-16：00
地 点: 理科大楼A1514室
题 目：Causal Effects and Posterior Causal Effects
报告人： 贾金柱 北京大学研究员
主持人： 刘玉坤 教授
主 办：统计学院
摘 要：
In this talk, I will talk on two concept: causal effects and posterior causal effects.
For causal effects, we study covariate adjusted average treatment effect estimate problem. We specify a working model for the potential outcome and the covariates. We show that even when the working model is misspecified, the difference estimator for the average treatment effect is consistent and asymptotically normal. We propose a well designed generalized estimation equation method, with which the estimated average treatment effect is always more efficient than the simple difference in mean estimator, under mild conditions. Extensive simulation studies verify our theoretical results.
For posterior causal effects, I will first introduce a few historical work on this concept. For the case with a single causal variable, Dawid et al. (2014) defined the probability of causation and Pearl (2000) defined the probability of necessity to assess the causes of effects. For a case with multiple causes which may affect each other, we define the posterior total and direct causal effects based on the evidences observed for post-treatment variables, which could be viewed as measurements of causes of effects. The posterior causal effects involve the probabilities of counterfactual variables. Thus, like probability of causation, probability of necessity and the direct causal effects, the identifiability of the posterior total and direct causal effects requires more assumptions than the identifiability of the traditional causal effects conditional on pre-treatment variables. We present assumptions required for the identifiability of the posterior causal effects and provide identification equations. Further, when the causal relationships among multiple causes and an endpoint may be depicted by causal networks, we can simplify both the required assumptions and the identification equations of the posterior total and direct causal effects. Finally, using numerical examples, we compare the posterior total and direct causal effects with other measures for evaluating the causes of effects and the population attributable risks.
报告人简介：
贾金柱，北京大学公共卫生学院生物统计系副主任，副教授/研究员，博士生导师。2009年1月北京大学博士毕业。 2009年1月至2010年12月，UC Berkeley 博士后。 2011年1月至2018年1月任职于北京大学数学科学学院概率统计系和北京大学统计中心，期间访问哈佛大学一年。2018年2月加入北京大学公共卫生学院。主要研究方向是因果推断、生物统计、高维统计推断、大数据分析、统计机器学习等。在变量选择方法的理论研究、高维数据和大数据统计学习的应用以及因果推断等领域发表论文多篇。担任现场统计学会因果推断分会副理事长、中国概率统计统计学会副秘书长、青年统计学家协会常务理事、北京应用统计学会常务理事、现场统计研究会计算统计分会理事、现场统计研究会高维数据统计会理事。主持基金委青年项目、面上项目资助各1项