Resources

On this page I provide links to learning resources I find very useful. This is surely not an exhaustive list. I’ll add to this list when I come across interesting resources.

Learning R

R comes with a steep learning curve but opens up a lot of possibilities for its users. You don’t need to learn each and every command — no one is able to do that. The best you can do is learn the basics, get started with a project and learn by doing. And then practice, practice, practice.

There are almost endless resources on R on the web. Here are some resources I recommend:

Videos

• Nick Huntington-Klein has excellent videos on R for econometrics and many other topics.

• Albert Rapp’s website and YouTube channel is a treasure trove for tips and tricks with R, especially for data wrangling, visualisation, and outputs with Quarto.

Textbooks and websites

• Here is a free e-book with an introduction to base R. R has gotten a lot more user friendly with the introduction of tidyverse. However, if you want to become proficient in R, knowing base R is very helpful.

• R for Data Science by Hadley Wickham and Garrett Grolemund is THE standard textbook for working with tidyverse.

• For econometrics, I recommend two e-books: 1) Introduction to Econometrics with R, an introductory e-book based on the Stock & Watson textbook, created by Christoph Hanck, Martin Arnold, Alexander Gerber, and Martin Schmelzer. 2) Introduction to Econometrics with R, a free e-book by a team of professors from Sciences Po (Florian Oswald, Vincent Viers, Jean-Marc Robin, Pierre Villedieu, Gustave Kenedi). The book combines everything you need: an introduction to R, econometric theory, coding examples, etc.

• The R Graph Gallery by Yan Holtz provides examples (visual and code) for pretty much any graph type under the sun.

• Telling Stories with Data by Rohan Alexander is a free e-book aimed at data scientists. It offers lots of excellent examples about workflows, exploratory analysis, modeling and applications.

• Allison Horst’s page on data wrangling with dplyr is excellent. Come for the coding, stay for the penguin illustrations.

• R is great for text analysis. You can learn tidytext in this excellent tutorial by Julia Silge. A more comprehensive package on text analysis is Quanteda, which has been co-written and is co-maintained by Stefan Müller. Stefan is also based at UCD and does very cool work at the intersection of political science and data science. See here for an example.

• Grant McDermott’s materials on Data Science for Economists have lots of interesting material on workflow, processing of large data (high-performance computing, Spark, Docker), and database management.

• Jon Hersh’s course on Machine Learning for Economistscovers the basics of machine learning in a very intuitive way.

Causal Inference

General

• The Nobel Prize 2021 was given to three masters of causal inference: David Card, Joshua Angrist, and Guido Imbens. Here is a video of a lecture to UCD undergraduate students I’ve given the day after the prize was announced.

• It is difficult to stay up to date with all the new methods in applied econometrics. Here is a fantastic public good by Christine Cai, who maintains a document with abstracts and references of methods papers of the last 5-6 years. Link here.

• Paul Goldsmith-Pinkham has an excellent course on applied empirical methods (basically causal inference), with YouTube videos and lecture slides.

• Want to use causal inference with Python? Check out Matheus Facure’s free e-book Causal Inference for the Brave and True.

Specific Methods

• Jonathan Roth provides excellent slides on new diff-in-diff methods, along with coding exercises and R packages. Also, see Ajad Naqvi’s website listing the various diff-in-diff packages in R, Stata and Julia.
• Matias D. Cattaneo, Nicolas Idrobo, Rocio Titiunik have an excellent review article on regression discontinuity designs.
• Peter Hull’s course materials on instrumental variables.