Econometrics (PhD)
First-year course of the Central-German Doctoral Program in Economics (CGDE), hosted at the Halle Institute for Economic Research (IWH)
Overview
The course comes in two parts. Econometrics I introduces state-of-the-art methods in causal inference for microeconometric applications. We revisit foundational techniques — linear regression, panel-data methods, and instrumental-variables estimation — with special emphasis on what OLS coefficients mean and on understanding uncertainty through standard errors. Econometrics II turns to modern causal-inference designs — regression discontinuity, difference-in-differences and event studies, and matching — and their identification assumptions and practical implementation.
Each part runs in four lecture sets, two weeks apart. A set is a Monday with a morning and an afternoon block (Parts I and II), a mandatory reading list, and an online quiz. The applied material — simulations and regressions we run together in class — is not on slides but in Jupyter notebooks in the course repository on GitHub (see Materials).
Classic textbooks such as Wooldridge (2010), Greene (2003), and Cameron and Trivedi (2005) cover the fundamentals of regression theory and remain the place to check derivations. The course itself follows the causal-inference tradition of Angrist and Pischke (2009), Cunningham, and Huntington-Klein: the question is always which design identifies a causal effect, and what a regression coefficient does and does not tell you about it. Both course textbooks are freely available online and do not need to be bought: Cunningham, Causal Inference: The Mixtape (2nd edition; the 1st edition is used for the regression review), and Huntington-Klein, The Effect (2nd edition).
The tables below list the lecture sets with their mandatory readings. The slides and the quizzes live on the OVGU e-learning page (see Materials); dates, times, and registration are on the CGDE course page.
Econometrics I
| Set | Title | Mandatory readings |
|---|---|---|
| 1 | Regression Review I and II | Mixtape 1st ed., ch. 2 (Probability and Regression Review); Mixtape 2nd ed., sec. 5.9 (Regression); The Effect, ch. 13 (Regression). Further: Brambor, Clark and Golder (2006); Huntington-Klein (2023); Mullahy and Norton (2024); Chen and Roth (2024) |
| 2 | Causality and Potential Outcomes I and II | Mixtape, ch. 3 (Directed Acyclic Graphs) and ch. 4 (Potential Outcomes and Randomization); The Effect, ch. 6 (Causal Diagrams) and ch. 10 (Treatment Effects) |
| 3 | Panel Data; Standard Errors | Mixtape, sec. 8.1 (Fixed Effects); Mixtape 1st ed., ch. 2 (clustering); The Effect, ch. 16 (Fixed Effects); Huntington-Klein (2023); Petersen (2009); Wooldridge (2023); Abadie, Athey, Imbens and Wooldridge (2023) |
| 4 | Instrumental Variables I and II | Mixtape, ch. 7 (Instrumental Variables); The Effect, ch. 19 (Instrumental Variables); Peter Hull's lecture notes |
Econometrics I closes with a 60-minute, closed-book written exam covering the whole part.
Econometrics II
| Set | Title | Mandatory readings |
|---|---|---|
| 5 | Regression Discontinuity I and II | Mixtape, ch. 6 (Regression Discontinuity); The Effect, ch. 20 (Regression Discontinuity); Peter Hull's RDD slides |
| 6 | Difference-in-Differences; Event Studies | Mixtape, ch. 9 (Difference-in-Differences Fundamentals); The Effect, ch. 17 (Event Studies) and ch. 18 (Difference-in-Differences) |
| 7 | Advanced DiD and Event Studies I and II | Mixtape, ch. 10 (Complex Diff-in-Diff Designs); Roth, Sant'Anna, Bilinski and Poe (2023); Roth (2022); Roth (2024); Asjad Naqvi's DiD tutorial |
| 8 | Matching Methods I and II | Mixtape, ch. 5 (Unconfoundedness); The Effect, ch. 14 (Matching) |
Econometrics II closes with a 60-minute, closed-book written exam covering the whole part. The reading list for Econometrics II is updated before the part starts.
Notebooks
The applied part of each set is taught from Jupyter notebooks in Python, one cell at a time, with simulated data where the truth is known: OLS by matrix algebra, logs and their interpretation, interaction effects, and more as the term progresses. The notebooks are committed with their output, so they can be read on GitHub without installing anything; the repository's README explains how to run them locally.
Quizzes
Each lecture set comes with one online quiz on the e-learning page: 20 true/false and multiple-choice questions, 20 minutes, one attempt. A quiz opens directly after its lecture set and closes on the Wednesday of the following week; the last quiz of each part closes on the Monday before the exam. Passing three of the four quizzes is the requirement for sitting the written exam of that part.
Materials
The lecture slides and the quizzes are on the e-learning page at OVGU, one course room per part. Participants are registered there as guest students. The room for Econometrics II is added before that part starts.
Econometrics I on e-learning ↗
The notebooks are in the public course repository on GitHub.
References
- Cunningham, S. (2026). Causal Inference: The Mixtape. 2nd ed., online. mixtape.scunning.com
- Cunningham, S. (2021). Causal Inference: The Mixtape. 1st ed. Yale University Press. mixtape-1ed.netlify.app
- Huntington-Klein, N. (2025). The Effect: An Introduction to Research Design and Causality. 2nd ed. Chapman & Hall/CRC. theeffectbook.net
- Abadie, A., Athey, S., Imbens, G. W., & Wooldridge, J. M. (2023). When should you adjust standard errors for clustering? Quarterly Journal of Economics, 138(1), 1–35.
- Angrist, J. D., & Pischke, J.-S. (2009). Mostly Harmless Econometrics: An Empiricist's Companion. Princeton University Press.
- Brambor, T., Clark, W. R., & Golder, M. (2006). Understanding interaction models: Improving empirical analyses. Political Analysis, 14(1), 63–82.
- Cameron, A. C., & Trivedi, P. K. (2005). Microeconometrics: Methods and Applications. Cambridge University Press.
- Chen, J., & Roth, J. (2024). Logs with zeros? Some problems and solutions. Quarterly Journal of Economics, 139(2), 891–936.
- Greene, W. H. (2003). Econometric Analysis. Pearson Education.
- Huntington-Klein, N. (2023). My unnatural war against the natural logarithm. Substack post.
- Mullahy, J., & Norton, E. C. (2024). Why transform Y? The pitfalls of transformed regressions with a mass at zero. Oxford Bulletin of Economics and Statistics, 86(2), 417–447.
- Petersen, M. A. (2009). Estimating standard errors in finance panel data sets: Comparing approaches. Review of Financial Studies, 22(1), 435–480.
- Roth, J. (2022). Pretest with caution: Event-study estimates after testing for parallel trends. American Economic Review: Insights, 4(3), 305–322.
- Roth, J. (2024). Interpreting event-studies from recent difference-in-differences methods. arXiv:2401.12309.
- Roth, J., Sant'Anna, P. H. C., Bilinski, A., & Poe, J. (2023). What's trending in difference-in-differences? A synthesis of the recent econometrics literature. Journal of Econometrics, 235(2), 2218–2244.
- Wooldridge, J. M. (2010). Econometric Analysis of Cross Section and Panel Data. 2nd ed. MIT Press.
- Wooldridge, J. M. (2023). What is a standard error? (And how should we compute it?) Journal of Econometrics, 237(2), 105517.