D02-03AM: Causal Inference

The course provides an introduction to the essential methods of causal inference, foundational for program evaluation. Designed for students, policymakers, and researchers, the course combines theoretical insights with practical applications. Participants will explore key methodologies including regression adjustments, experiments (RCTs), matching, regression discontinuity designs, instrumental variables, and difference-in-differences. The course begins with causal graphs to develop an intuitive understanding of cause-and-effect relationships. Each session delves into a specific method, its assumptions, and its applications, using real-world case studies to illustrate concepts. Hands-on exercises in R will help participants gain skills, reinforcing concepts through data analysis.

By the end of the course, participants will be equipped to critically assess and conduct impact evaluations of policies and programs. Prior familiarity with basic statistics and R is recommended.

The course begins with causal graphs to develop an intuitive understanding of cause-and-effect relationships. Each session delves into a specific method, its assumptions, and its applications, using real-world case studies to illustrate concepts. Hands-on exercises in R will help participants gain  skills, reinforcing concepts through data analysis.

By the end of the course, participants will be equipped to critically assess and conduct impact evaluations of policies and programs. Prior familiarity with basic statistics and R is recommended.

Learning Outcomes:

• Understand the foundational methods of causal inference.
• Evaluate and interpret evidence from development policies and programs.
• Apply causal inference techniques to real-world data and policy challenges.

Day 1: Regressions and Experiments

• Objective: Introduce the foundations of causal inference, common cause adjustments and understand randomized treatments in experiments
• Content:
  • Introduction to causal graphs and covariate adjustment.
  • Practical exercise: Using regression to adjust for confounders
  • Average treatment effect and randomization
  • Applications to social policy: Women as policymakers and their impact.
  • Hands-on exercise
• Readings: Excerpts from Chapter 1, 5 and Chapter 6 of Demystifying Causal Inference.

Day 2: Matching Methods

• Objective: Use observational data to mimic experimental conditions.
• Content:
  • Matching techniques: Exact, propensity score, and coarsened exact matching.
  • Application: Decentralized forest management and environmental outcomes.
  • Hands-on exercise
• Readings: Chapter 7 of Demystifying Causal Inference.

Day 3: Regression Discontinuity Design (RDD)

• Objective: Leverage sharp treatment assignment for causal inference.
• Content:
  • Key assumptions of RDD.
  • Application: Term limits and political performance.
  • Hands-on exercise
• Readings: Chapter 9 of Demystifying Causal Inference.

Day 4: Instrumental Variables (IV)

• Objective: Understand the use of instruments to identify causal relationships.
• Content:
  • Concepts of exogeneity and exclusion restriction.
  • Application: Colonial development and institutional outcomes.
  • Hands-on exercise
• Readings: Chapter 8 of Demystifying Causal Inference.

Day 5: Difference-in-Differences (DiD)

• Objective: Analyze policy impacts using temporal and group variation.
• Content:
  • Parallel trends assumption and robustness checks.
  • Application: Bank failures during the Great Depression.
  • Hands-on exercise
• Readings: Chapter 10 of Demystifying Causal Inference.

Required Readings:

1. Demystifying Causal Inference (2023) by Vikram Dayal and Anand Murugesan.
2. Mastering ‘Metrics: The Path from Cause to Effect (2014) by Joshua Angrist and Jörn Steffen Pischke.
3. The Effect: An Introduction to Research Design and Causality (2021) by Nick Huntington-Klein.

Additional Notes:

• Participants should read the mandatory materials before each session.
• Familiarity with basic statistics and R is highly recommended, as the course includes hands-on coding exercises.
• Laptops with R installed are required for in-class exercises.

By the end of the course, participants will have a solid foundation in causal inference methods and the practical skills to apply them to complex policy and program evaluation challenges.

This description is subject to change at the discretion of the Instructor

2 Credits

For completion of all work before and during the course, as outlined by the Instructor, and 90% participation and attendance of the course.

2 Additional Credits

Course specific extra assignments. These can include submitting assignments before the course, daily assignments, and/or a final assignment to be completed after the course as decided by the Instructor.