- https://github.com/JoshMerfeld/applied-microeconometrics
- ekdis.ac.kr (KDIS students only -- you will turn in your assignments here, but everything else is hosted on GitHub)
This course is aimed at masters or Ph.D. students who wish to improve their understanding of modern empirical applied micro and the course has two main goals, both of which aim to prepare you to do applied micro-econometric research. First and foremost, we will discuss modern empirical methods. While most of the focus will be on causal inference, we will also spend time on other topics, like bootstrapping and penalized regression. The focus is very much applied; while we will cover some theory, the main goal is for you to understand how to interpret and implement these methods, which leads to the second goal of the course.
By the end of the course, you will be expected to be comfortable using the statistical package R (through RStudio). There are three main statistical languages used in applied econometrics today: Stata, R, and Python, with the first two being more popular than the third. While it is perfectly acceptable to use any of these languages, I have chosen to teach this course with R. In addition to learning R, you will also turn in assignments created using R Markdown.
By learning the techniques and the language needed to implement these techniques, you should be equipped to start doing your own research.
There are quite a few (free!) resources available online to help you learn R.
In addition to online resources, TA sections in this course will be devoted to help with R. Bring all your questions there!
There has been an explosion of texts related to causal inference in the past decade or so. In addition to the articles we will read throughout the semester, the followings texts are helpful references, with the first three being particularly notable:
- Joshua Angrist and Jörn-Steffen Pischke, Mostly Harmless Econometrics
- Joshua Angrist and Jörn-Steffen Pischke, Mastering 'Metrics: The Path from Cause to Effect
- Scott Cunningham, Causal Inference: The Mixtape, https://mixtape.scunning.com/ (this book has lots of example code, which you may find helpful)
- Nick Huntington-Klein, The Effect: An Introduction to Research Design and Causality, https://theeffectbook.net/ (note that this is a more introductory text than the others)
There are also two slide decks that are extremely helpful:
- Paul Goldsmith-Pinkham's slides: https://github.com/paulgp/applied-methods-phd (these slides focus on causal inference)
- Grant McDermott's slides: https://github.com/uo-ec607/lectures (these slides focus on data science and R)
You can find the slides (and any data we will be using) for each week under their respective folders (weeks/). Most weeks will have just a single slide deck. Note that in each week's folder, you can also find the raw .Rmd file that I used to create the slides. You might find these helpful, though you are by no means required to look at them.
- Week 1: Week 1 has two slides.
- Week 2: You can find the slides for the the week here.
- Week 3: You can find the slides for the the week here.
- Week 4: You can find the slides for the the week here.
- Weeks 5 and 6: You can find the slides for the the two weeks here.
- Weeks 7 and 8: You can find the slides for the the two weeks here.
- Week 9: You can find the slides for the the week here.
I will also post your assignments here, under the assignments folder.