Applied Causal Inference
Course Description
This course will present the fundamental topics of causal inference for randomized and non-randomized studies. We will introduce the potential outcomes framework, identification of estimands (e.g., via g-formula), directed acyclic graphs (DAGs), and the basics of experimental design (e.g., Fisher-exact p-value, confidence interval). We will discuss how to approximate a randomized controlled trial with non-randomized data using propensity score methods (matching, weighting) and augmented inverse probability weighting, and we will explore additional topics, including mediation analysis. Emphasis will be given to clinical research applications, with labs covering coding examples using the statistical software R. ​
Instructor
Marie-Abèle Bind, PhD
Assistant Investigator, Biostatistics, Massachusetts General Hospital
Assistant Professor of Medicine, Biostatistics, Harvard Medical School
Marie-Abele Bind, PhD is an  Assistant of Investigation at the MGH Biostatistics Center and an Assistant Professor at the Harvard Medical School. Her research interests focus on developing causal inference methods for quantifying the effects of randomized and non-randomized exposures on various outcomes and understanding the mechanisms explaining these effects. This year, she teaches "Design of Experiments" (STAT 140) at the Harvard College. Her research was funded by the NIH Early Independence Award program. She completed her joint PhD in Biostatistics and Environmental Health at the Harvard School of Public Health, working with Professors Joel Schwartz and Brent Coull. She then became a Ziff postdoctoral Fellow at the Harvard University Center for the Environment. In 2016, she was awarded an Early Independence Award (NIH High-Risk High-Reward research grant) and became a Research Associate in the Department of Statistics. From 2017 to 2021, she became a John Harvard Distinguished Science Fellow.
Instructor
David Cheng, PhD
Assistant Investigator, Biostatistics, Massachusetts General Hospital
Assistant Professor of Medicine, Biostatistics, Harvard Medical School
David Cheng, PhD is an assistant investigator at MGH and an Assistant Professor of Medicine at HMS. His research involves developing methods for causal inference and data integration in complex real-world data settings. He works on collaborative research across multiple areas in clinical and health policy research. He has presented his research at national and international venues and published his work in Biometrics, Annals of Applied Statistics, and JAMA Network Open.
