STAT 186/GOV 2002: Causal Inference



Substantive questions in empirical scientific and policy research are often causal. Does voter outreach increase turnout? Are job training programs effective? Can a universal health insurance program improve people's health? This class will introduce students to both statistical theory and practice of causal inference. As theoretical frameworks, we will discuss potential outcomes, causal graphs, randomization and model-based inference, sensitivity analysis, and partial identification. We will also cover various methodological tools including randomized experiments, regression discontinuity designs, matching, regression, instrumental variables, difference-in-differences, and dynamic causal models. The course will draw upon examples from political science, economics, education, public health, and other disciplines.

  Lecture Slides

Potential Outcomes
Permutation Tests
Permutation Inference
Inference for the Average Treatment Effects
Stratified Randomized Experiments
Simple Linear Regression
Covariate Adjustment in Randomized Experiments
Noncompliance in Randomized Experiments
Instrumental Variables
Regression Discontinuity Designs
Regression with Observational Data
Matching Methods
Weighting Methods
Differnece-in-Differences Designs
Causal Directed Acyclic Graphs
Heterogeneous Treatment Effects
Partial Identification

© Kosuke Imai
 Last modified: Fri Dec 6 22:24:34 EST 2019