Causal Inference in Observational Studies
Michael Elliott
June 19, 2026 – 9am-1pm EST, 6050 ISR-Thompson/Zoom
Please join for the next installment of the PDHP workshop series: Causal Inference In Observational Studies, presented by Michael Elliott of the University of Michigan Biostatistics & the Program In Survey & Data Science. This workshop will cover techniques for causal inference using observational data, including theoretical concepts (causal inference via counterfactuals, and how causal inference can be produced from randomized designs), and applied techniques such as estimating causal effects via propensity modelling and matching techniques. Examples and code using R will also be provided throughout the workshop.
Topics include:
- Causal inference via counterfactuals
- Why randomized designs yield causal inference
- Estimating causal effects via propensity modelling & matching
- Overlap and its impact on inference
- Hands-on practice with examples and code using R
Video & Slides:
The workshop video is available here
The workshop slides are available for download hereThis linked document/file has unknown accessibility or has not been evaluated
Lab Materials:
A sample dataset for workshop examples is linked hereThis linked document/file has unknown accessibility or has not been evaluated
R codeThis linked document/file has unknown accessibility or has not been evaluated
Recommended Software:
The workshop will provide examples in R as configured below:
–– R Studio (strongly recommended)
–– R packages can be installed using the following code
# install R packages
install.packages(c("multcomp","survey"))