Causal Inference

4 units · Graduate professional courses (400-499)

Lecture, three hours; discussion, one hour. Recommended preparation: familiarity with basic probability theory, regression modeling, and statistical computing environment (R or Python). Limited to Master of Applied Statistics students. Offers principled foundation for causal reasoning using Pearl’s causal hierarchy (PCH) and structural causal models (SCMs), and develops practical tools for answering causal questions from real-world data. Students learn to distinguish observational, interventional, and counterfactual reasoning; to design and analyze experiments; and to draw valid causal conclusions when experimentation is not possible. Also covers modern topics at intersection of causal inference and artificial intelligence. Applications are drawn from technology, business, and health sciences. Letter grading.