Biostatistics Short Course: Applied Causal Inference for Real-World Data

In recent decades, techniques have been developed for identifying and estimating causal effects from real-world data (RWD). This course aims to introduce participants to these techniques. The course will first explain the use of directed acyclic graphs, counterfactuals, and identification assumptions to identify causal estimands. The course will then introduce various statistical estimators for estimating these estimands, including estimators based on outcome regression, inverse probability weighting estimators, and doubly robust estimators. R will be employed to compute causal effects, providing participants with practical, hands-on experience in causal inference through examples. Upon completing this course, participants will possess the skills to identify, estimate, and compute causal effects using RWD, thereby enhancing their research and decision-making capabilities.

Audience and Prerequisites:

This course is intended for statisticians, computer scientists, biostatisticians, epidemiologists, and social and political scientists with a foundation in basic programming in the R language, statistical inference tools (e.g., conditional expectation, point estimation, confidence intervals, hypothesis testing), and regression modeling.

Speaker:

Michele Santacatterina, PhD, NYU Grossman School of Medicine