20190628 Hongwei Zhao:Causal Inference for Observational Data – a Review of Basic Theory and Some Newer development
报告时间:2019年6月28日 15:00-16:00
报告地点:明德主楼1016会议室
报告主题: Causal Inference for Observational Data – a Review of Basic Theory and Some Newer development
报告摘要:
This talk provides a review of the statistical methods for drawing “causal inference” for observational studies. We will start with a review of the fundamental theory based on the potential outcome framework developed by Donald Rubin. Next we will discuss propensity scores and their uses in developing matching, stratification, inverse probability weighting estimators, and doubly robust estimators. We will learn the theory behind these methods and the advantages and disadvantages for each method. Finally we will cover some newer development of these methods, e.g. targeted maximum likelihood approach using superlearner, and methods for time varying treatments.
报告人简介:
Dr. Hongwei Zhao is currently a Professor in the Department of Epidemiology and Biostatistics, School of Public Health, Texas A&M University. She received her doctoral degree in Biostatistics from Harvard in 1997, and became a faculty member at University of Rochester before moving to Texas in 2008. Dr. Zhao is currently serving as a Visiting Professor at College of Statistics, Renmin University of China. Dr. Zhao has collaborated extensively with many researchers from different fields such as Community Medicine, Epidemiology, Neurology, Cancer, Cardiovascular Diseases, and Health Policy and Management. She has made significant contribution in the area of estimating quality-adjusted survival time and medical costs analyses with censored data. Her current research interest is in the area of causal inference for observational studies.