Sergey Tarima, Associate Professor of Biostatistics, Division of Biostatistics, Institute for Health and Equity
About the speaker
Dr. Tarima holds a candidate of technical sciences degree from the Tomsk State University (2002) and a PhD in statistics from the University of Kentucky (2005). His interests include statistical aspects of adaptive designs and in the use of auxiliary information in statistical inference.
Abstract
Observational Studies are distinctly different from the Randomized Controlled Trails (RCT). RCTs are used for estimating Averaged Treatment Effects (ATE) and heavily rely on impartial randomization to treatment groups. Randomization is not possible in observational studies preventing direct ATE estimation. Instead, Averaged Causal Effect (ACE) can be estimated which mimics ATE. ACE coincides with ATE in RCTs and is an extension of ATE to observational studies. In this presentation, we will discuss causal inference with emphasis on ACEs. We will apply propensity scores for estimating ACEs on observational data. Propensity score based inverse probability weighting will be used for illustrative purposes.
NIH Funding Acknowledgment:Important Reminder – Please acknowledge the NIH when publishing papers, patents, projects, and presentations resulting from the use of CTSI resources by including the NIH Funding Acknowledgement.
