Skip to main content
Impact Evaluation: Policy Applications with R
Course Description

Elective course

Quantitative Policy Analysis specialization for DPP students

This course explores the role of causal inference methods and data in evidence-based policymaking. Using the statistical software R, students will be introduced to key methods of causal inference used in program and policy evaluation. Through the use of case studies, the course emphasizes the practical application of these evaluation techniques.

Students need to have a beginner's familiarity with R before the start of the course (see helpful materials below for getting started). The course begins with a gentle introduction to R, followed by the potential outcomes and the causal graph framework to develop an understanding of causality. Topics covered include experiments (RCTs), difference-in-differences, co-variate adjustment through regressions, and matching.

Session format: Short lecture on the concepts followed by lab work with R

Course methods and materials

This course recognizes the importance of hands-on practice in program and policy evaluation. Students will engage in in-class lab work, homework assignments, group projects, and exams to master the techniques. The course will present the key concepts through a combination of lectures and case studies. The lab work with R (20% of the course) will focus on developing essential data skills. Collaboration in groups for assignments is encouraged. Active class attendance and participation are highly recommended, and unexplained absences will be recorded.

Students are required to prepare for class with the assigned readings.

We will use the book, "Demystifying Causal Inference: Public Policy Applications with R" for the course. There are great additional materials for those interested in causal inference, which we will draw from, including:

1. Mastering `Metrics: The Path from Cause to Effect (2014) by Joshua Angrist and Jorn Steffen Pischke.

2. The Effect by Nick Huntington-Klein

2. Causal Inference: The Mixtape (2021) by Scott Cunningham

3. Quantitative Social Science (2017) by Kosuke Imai

The course runs in the second part of the Fall term, Week 7 - 12.

Learning Outcomes

Course goals
1. Understand and implement basic methods used in impact evaluation
2. Become critical consumers of development policies and programs
3. Use R to analyze and evaluate policies and graph data


Assignments (40%); Group project (20%); Final exam (40%)


Adequate training in statistics or econometrics (at a minimum) or the introductory quantitative methods course at DPP. Familiarity with R, see helpful materials below to get started: 

We will work with RStudio, so you should download R and RStudio.

Datacamp has some good R-related courses. We will use Tidyverse (a world within R) in the course -- so reviewing some early chapters in Hadley Wickham's book can be beneficial (if you can import data and run a simple regression, you are ready for the course).

It is good to get an idea about R Markdown.

The following SSRN paper on R for environmental economics

Links with the YouTube video

And the GitHub repository for R code
Sections 1 to 3.1 might be helpful if R is relatively new to you or if it has been a while since you used R. Section 3.2 presents basic data analysis with a field experiment that studied the effect of health awareness on the choice of clean cooking fuel. The data is publicly available so you can download the data from the online website linked to the paper.

A few chapter manuscripts from Quantitative Economics with R (on Moodle). 

Course Level
Course Open to
Students on-site
Academic Year
US Credits
ECTS Credits
Course Code