Offered under: 15.C08, 17.C08
Term(s): Spring only
Level: Undergraduate
Units: 12
Prerequisite: 6.3800, 6.3900, 6.C01, 14.32, 17.803, 18.05, 18.650, or permission of instructor
Instructors: Joseph Doyle (Sloan), Roberto Rigobon (Sloan), Teppei Yamamoto (Political Science)

Provides an accessible overview of modern quantitative methods for causal inference: testing whether an action causes an outcome to occur. Makes heavy use of applied, real-data examples using Python or R and drawn from the participating domains (economics, political science, business, public policy, etc.). Covers topics including potential outcomes, causal graphs, randomized controlled trials, observational studies, instrumental variable estimation, and a contrast with machine learning techniques. Seeks to provide an intuitive understanding of the core concepts and techniques to help students produce and consume evidence of causal claims.

Satisfies requirements in the 6-3, 6-4, 15-1, 15-2 and 17 degree programs.