Causal Inference with R

Across public health, medicine, and social and behavioral sciences, researchers aim to answer causal questions. However, inferences about causation are challenging and require several assumptions to draw unbiased causal effects from observational data. This workshop discusses the difference between association and causation and introduces various methods to infer causal effects with observational data. We will then study R packages that implement propensity score techniques to estimate an average treatment effect – such as matching, subclassification, and inverse probability weighting. The workshop also provides several implementation options depending on the data type and the target causal effects of interest.

About our speaker:

Youjin Lee is an Assistant Professor in the Department of Biostatistics at the Brown School of Public Health. Her research focuses on developing causal inference methods with complex data where standard assumptions are often violated. She published R packages for causal inference with social network data and multilevel settings. Originally from South Korea, Youjin received her Ph.D. in Biostatistics from Johns Hopkin University. Before joining Brown University, she did her postdoctoral training at the University of Pennsylvania.

Note from organizers:

We're excited to see so much enthusiasm for this topic! Please note that the zoom room is capped at 100 participants - if you would like to attend, please make sure to be on time. We will be recording the meetup, so if you aren't able to attend the live webinar, we will share the recoding on our YouTube channel after the session.