Difference-in-Differences

Difference-in-Differences (DiD) is among the most popular strategies to identify causal effects in observational studies. However, the literature is evolving fast, making it challenging to keep up with best practices. This is your chance to get up to speed! Enroll now to deepen your understanding of modern DiD tools and engage with one of the most accessible leading experts in the field, Pedro Sant’Anna. Not only will we cover the tools but also how to use them in practice!

Price: $995  $595

  • 8 sessions - March 13, 14, 15, 16, 17, 20, 21, 22 2023
  • 2 hours live sessions, starting at 11am EST
  • Two 1-hour long Q&A sessions
  • 7 pre-recorded lectures on advanced topics
  • 1 year access to recordings of every session
  • All your questions answered, guaranteed

Student Price (also applicable for developing countries): $295 – contact us for the link

ENROLL NOW - Limited seats!

What this course is about

Difference-in-Differences (DiD) methods are widely used to answer what-if type of questions in economics, political science, and many other social and medical sciences. These methods are also very popular in industry, where causal inference play a prominent role.

Although very popular, the last few years have seen a booming of new papers on DiD and related designs, making it challenging to keep up with rapidly evolving best practices. The main goal of this course is to provide a fast-track towards these best practices, enabling each and every attendee to be comfortable with a wide range of DiD tools.

As we believe that the best way to really learn any data science tool is to blend its theory with real-life applications, each lecture session will include a hands-on exercise that illustrates the content covered.  We will provide practical guidance on implementing these tools in R and Stata!

Content

We will cover the theory and practice of DiD methods in detail. We will practice the implementation of these tools using code and sample data.  The portions of the course which are marked as extra will be made available via recordings.

Topic 1: Introduction to DiD and a brief overview of causal inference

We will discuss DiD popularity by briefly highlighting several applications in different fields. We will also lay down the potential outcome framework that will serve as the foundation for all our discussions. More specifically, we will:

  • Highlight DiD popularity in different fields;
  • Introduce the potential outcome framework and how we use it to embrace treatment effect heterogeneity;
  • Discuss the challenges to conduct causal inference with observational data, and how DiD methods address these.

Topic 2: The Classical 2x2 DiD setup

We do a deep-dive into the classical two-periods and two-groups DiD setup, paying particular attention to the commonly used assumptions to justify its reliability. In this section of the course, we will discuss:

  • The role of identifying assumptions: no anticipation and parallel trends;
  • Estimation of average treatment effects using simple comparison of means and regressions;
  • Inference procedures and clustering;
  • Falsification tests;
  • When parallel trends assumption is sensitive to functional form restrictions (extra).

Topic 3: 2x2 DiD setups with covariates

In many situations researchers wish to leverage available information about observed characteristics in DiD setups. Here, we will describe how you can reliably do this. We will discuss the following topics:

  • Allowing for covariate-specific trends;
  • Pitfalls of some two-way fixed-effects linear regression specifications;
  • Estimating treatment effects using the
    • outcome-regression approach;
    • inverse probability weighting approach;
    • doubly robust approach;
  • How to use machine learning procedures to do DiD (extra);
  • Panel data vs. Repeated cross-sectional data (extra).

Topic 4: DiD with multiple time periods

It is often the case in applications that we have access to more than two time periods. In this section we will discuss how we can leverage the additional information coming from these extra time periods, in setups without variation in treatment timing. Our lectures will shed light on the following questions:

  • Do we need to change the parallel trends assumption?
  • Can we allow for treatment anticipation?
  • How can we characterize treatment effect dynamics?
  • Can we assess the validity of parallel trends assumptions?
  • What if parallel trends only hold “approximately’’?

Topic 5: DiD with variation in treatment timing

It is not uncommon to have units being exposed to treatment at different points in time. How do DiD procedures perform in these more challenging setups? Does the choice of estimation method matter? How so? The recent DiD literature has provided many insights in these cases, and we will cover a good chunk of that, particularly in the case with staggered treatment adoption. Our discussion topics include:

  • What are the causal parameters of interest?
  • What type of parallel trends are we willing to impose?
  • Pitfalls of two-way fixed effects linear regression specifications;
  • Recovering meaningful causal parameters;
  • Highlighting treatment effect dynamics via event-studies;
  • Highlighting other sources of treatment effect heterogeneity;
  • Falsification tests;
  • Triple-Differences (extra);
  • What if treatment timing is random? (extra)
    • Can we do better than DiD? (extra)
    • How can we do randomization tests? (extra)
    • Do this actually matter in practice? (extra)
  • Challenges with setups where treatment can turn on and off (extra).

About Your Instructor

Pedro H. C. Sant'Anna, Ph.D.

Pedro H. C. Sant’Anna, Ph.D., is an Associate Professor of Economics at Emory University and an Amazon Visiting Academic. Before joining Emory and Amazon, he was at Vanderbilt University and Microsoft.

Pedro is a passionate econometrician, working in causal inference and semi- and non-parametric methods (also known as machine learning). Much of his recent work aims to develop, better understand, and further improve Difference-in-Differences methods. In fact, Pedro is among the most impactful researchers working on Difference-in-Differences methods, with more than 5,000 citations on the topic. 

He has published in top journals in economics and has given guest lectures and seminars on DiD topics at leading universities around the world, including Harvard University, Yale University, University of Chicago, MIT, UC Berkeley, among others. He is also a coauthor of several open-source packages for Difference-in-Difference methods, allowing him to have a first-hand experience on practicalities of these modern tools. His industry experience also allows him to effectively communicate with a broad audience with many different backgrounds. 

Pedro received his BA in Economics from Ibmec-MG (Brazil) in 2009, his M.A. and Ph.D. in Economics at Universidad Carlos III de Madrid (Spain) in 2011 and 2015, respectively. He is a recipient of the 2016 Arnold Zellner Thesis Award in Econometrics and Statistics, awarded by the American Statistical Association.

For more information about Pedro, access his personal website: https://psantanna.com/ 

What people say about the course

Difference-in-Differences by Causal Solutions is a memorable course and probably the most complete option currently available on the subject. By carefully going over the DiD foundations, the course lay the groundwork that enables students to understand what problems will arise when DiD is used in more complex settings, such as when there are multiple time periods or there is variation in treatment timing, and how to tackle them. Also, coding exercises (in Stata and R) are provided, so we understand how to implement what we are learning. However, what I think makes the course memorable is Pedro. He is a superb teacher that is able to breakdown complex topics so that students can understand and follow along. His passion and energy are inspiring. It is clear to see that he loves what he is teaching and that makes the course much more engaging. I can't recommend enough the experience of having him as an instructor.
Breno Salomon ReisBrazil's National School of Public Administration (Enap)
Pedro is an excellent instructor. The course was super interesting as it offered a good overview of the most recent trends in DiD literature, explained in a clear and easy-to-understand way. Pedro was always available to answer all our questions and to stay extra time with us when needed. The course offered a good combination of theory and application, and provided us with all the reference papers and also some examples of how to run R or Stata codes. For me was a great opportunity to catch up with the recent development on this topic, and all the lectures were extremely interesting. Pedro is very nice and makes you feel comfortable during the lectures: you won't get bored! We have now access to all the material for 1 year and this is very useful
ElenaEuropean Commission-JRC
Fantastic course! Learning the latest developments on Difference-in-difference from someone who has been in the heart of it has been a real privilege. I did the course fully asynchronously and enjoyed every second of the sessions! Great practicals and provided both in R and Stata which also helps the transition between the two softwares. Can't recommend this course enough!”
Magdalena OpazoThe University of Sheffield
“For anyone interested in understanding and/or keeping up with the literature on Difference-in-Differences, I highly recommend taking this course. Pedro is a great instructor, addressing all questions in great detail. The material is great whether you are an industry professional or an academic.”
Sue MárquezData Science @ LinkedIn
Pedro is passionate about teaching and really concerned about his students. He is very successful in the arduous task of teaching the basics and more recent developments of the DiD literature. I highly recommend this course for anyone interested in applied empirical research.
Carlos LadeiraHEC Montreal
Pedro has a really nice enthusiasm and energy! His knowledge of many aspects of DiD is unique. I had a good grounding before this course, but I still learned a lot. Also, he was good about allowing people a reasonable break in the middle of sessions which other courses don’t do (and suffer because of it).
David FraymanUniversity College London
I really liked the structure of the course, covering the basic 2x2 case and building on that to explain more complex situations. I also liked the fact that the course clearly separated identification and estimation steps, making it easier to reason about causal assumptions. There were also some labs in R which helped consolidate the theory. And there were always opportunities to ask questions during the classes, Q&A sessions, and offline on Slack/Discord. It was a very helpful and fun course on DID!
Daniela RodriguesImperial College London
“If you want to learn DiD, this is the course. Pedro is a star in this field, and he explains classic DiD and recent developments in concise and intuitive ways. Pedro is an excellent teacher; he is at the cutting edge of new developments, and he makes extraordinary efforts to explain things clearly (which, we know, takes a lot of preparation). ”
Aníbal Pérez-LiñánUniversity of Notre Dame
Pedro provided an intuitive structure that was built in a logical and easy to follow manner. He set a fast but necessary pace for each lesson along with clear instructions encouraging participation. The rhythm / break setting was ideal as was his selection of questions to answer live or address later. This allowed us to stay on track while still making sure everyone's questions were (eventually) covered, either in the breaks or asynchronously via Slack. I really appreciated how efficiently he handled such a diverse group, and it is a testament to how deeply Pedro understands the material he is teaching. I can't speak highly enough of this course and Pedro's teaching approach.
Setu PelzIIASA
“This is an excellent course. I was already familiar with DID models, but the course provided new developments I was not aware of and that I found very useful. I will use these new methods in my work.”
Gustavo AngelesUniversity of North Carolina, Chapel Hill
“Pedro knows the recently published DID literature extremely well---he has co-authored many of these papers but is also very knowledgeable about the papers written by other method researchers. In addition, he is an exceptional presenter and handles questions very well. I feel that I was able to get a solid start on these newly published papers in a few days that would have taken me weeks if I had to read the papers myself.”
M. Zia HydariUniversity of Pittsburgh
“Awesome blend of hands-on treatment of estimation and background. Our lecturer gave a top overview of the recent developments and literature, which I could not have digested so quickly on my own.”
Jüerg SchweriSwiss Federal University for Vocational Education and Training
“Pedro is an awesome instructor and super patient. He not only discussed all state-of-the-art difference in differences theoretical advances but also provided tons of hands-on exercises for us. Highly recommend this course.”
Li FengTexas State University
“This course has enhanced my understanding of Difference in Differences methods and the cutting-edge innovations that have been made in recent years. It also provided me with the material to implement the analysis empirically. Pedro offered great insights and it is always available and friendly. I highly recommend this course!”
Elena BassoliThe University College London
“What I liked the most about this course is all theories/assumptions and estimation procedures, which were explained very clearly for conditional parallel trend in the 2x2 setting. I really learned a lot!”
Yu YePublic Health Institute
“The depth of knowledge illustrated by the teacher was phenomenal. Pedro was willing and able to answer a very wide field of questions on the topic clearly and in detail.”
Robert WishartWishart Research Consulting
“Very nice overview of recent and important literature on a workhorse model in applied micro from one of the leading researchers in the area. Pedro was also extremely helpful and very responsive to questions.”
Austin BeanTemple University
Previous
Next