Causal Inference for Data Analysis

2-0-4 units · Graduate

Introduces causal inference with an emphasis on probabilistic systems analysis. Readings about conceptual and mathematical background are given in advanced of each class. Focused on understanding theory based on real-world applications. The subject is project-based and focused on cause-effect relationships, understanding why probabilistic outcomes happen. Topics include correlation analysis, Reichenbach's principle, Simpson's paradox, structural causal models and graphs, interventions, do-calculus, average causal effects, dealing with missing information, mediation, and hypothesis testing. Students taking graduate version complete additional assignments.