Finding the effects of just about anything...
The sessions will be led by researchers at the frontier of causal-inference methods.
Our workshops feature exercises to teach practical skills that are ready to generate value for your research or company.
Attending our workshop won't break the bank. We even offer student pricing!
I feel like I have a better grasp on what the cutting edge and trends are in the field. The replications of studies were super insightful and the quantity of amazing resources provided was really generous and genuinely useful.
Dr. Cunningham made the process of learning, failing, and trying seem normal, and okay. His presentation is brilliant and can reach every single student in the class.
Scott is an amazing teacher! What I valued most was the explantion of the intuition behind the concepts (I am a Phd student and I have been studying economics for a while now, and I was able to understand things in ways I never did before).
I personally feel like I went from not knowing much about this method/design to feeling like I could attempt a study like this using some advanced techniques.
Programming example was something special. Our teacher never taught how to implement econometric method in real world research. And this is what I have learnt from Prof. Cunningham class.
Many people are looking for an on-ramp into the world of causal inference methodologies and need a clear sense of direction, as well as an opportunity to get on board at their own pace. My style of teaching uses clear exposition, examples of studies, and metaphors and stories that can elucidate more abstract ideas. I draw on pop culture, studies in health as well as economics, discussions of weird natural experiments creating surprising opportunities to answer elusive questions, and as I said, programming exercises. My classes are paced deliberately slower because I want students to gain depth and not merely topical knowledge. And so in addition to me talking, I use coding labs with some assignments and dive into the programming “in front of them” and with them to show how I think, the kinds of questions I have, and the decisions I make when writing code. And this has been a considerable success for many people as testimonies show.
It is my opinion that many people today learn causal inference, not simply through the calculus and exposition of the logic of the statistical modeling, but also through step by step walk through exercises using code. Code. Code has become for many of us the lingua franca of statistics and research, moreso than the heady equations of the underlying models themselves. To learn either but not the other is to often be substantially handicapped in one's own work. One must know what something does, why it does, but also, how to do it. And so my workshops are not merely lessons in statistics. They are also opportunities to code together in labs.
We will learn to code via implementation of methods, e.g. regression discontinuity, instrumental variables and difference-in-differences, using R, Stata and python. But, in the process of learning these designs well in these languages, the accidental byproduct will be a greater depth of understanding of the languages themselves too. Just like you often cannot see a star in sky when you stare at it directly, but can when you look just to the left or the right, so is for many of us the way in which we learn new programming languages.
Mastering some field, like causal inference, with its tedious details and subtleties, not to mention the coding that goes with it, is for many of us simply too time consuming. In other words, it isn't that we couldn't, if we had an infinite amount of time, master these subjects. It is that we don't have an infinite amount of time. The value of these workshops is having an explainer. I use a variety of rhetoric and pedagogies to do this. Sometimes, I take us through the algebra of some estimator because I know until you see it with your own eyes you simply will not believe it. And other times, I belabor a point using metaphors, stories and pictures. There is a role for all these things in explanations. And I grab hold of anything and everything that I believe can help you have epiphanies, breakthroughs and most of all success in how you define it.
Our founder, Scott Cunningham, is the author of Causal Inference: The Mixtape.
Causal inference encompasses the tools that allow social scientists to determine what causes what. In a messy world, causal inference is what helps establish the causes and effects of the actions being studied—for example, the impact (or lack thereof) of increases in the minimum wage on employment, the effects of early childhood education on incarceration later in life, or the influence on economic growth of introducing malaria nets in developing regions. The book introduces students and practitioners to the methods necessary to arrive at meaningful answers to the questions of causation, using a range of modeling techniques and coding instructions for both the R and the Stata programming languages.
You can read the entire textbook for free online here.
Scott also writes on a blog covering methods on substack.
Sign up for Scott Cunningham's substack blog to keep up to date with the latest in causal inference and to receive news of new mixtape sessions being announced.