| Dozent/in |
Prof. Dr. Helmut Farbmacher |
| Veranstaltungsart |
Doktorierendenkolloquium |
| Code |
FS261627 |
| Semester |
Frühjahrssemester 2026 |
| Durchführender Fachbereich |
Gesundheitswissenschaften |
| Studienstufe |
Doktorat |
| Termin/e |
Mo, 08.06.2026, 08:15 - 17:00 Uhr, Inseliquai 10 INE 214
Di, 09.06.2026, 08:15 - 17:00 Uhr, Inseliquai 10 INE 214
Mi, 10.06.2026, 08:15 - 17:00 Uhr, Inseliquai 10 INE 214
Do, 11.06.2026, 08:15 - 17:00 Uhr, Inseliquai 10 INE 214
Fr, 12.06.2026, 08:15 - 17:00 Uhr, Inseliquai 10 INE 214 |
| Weitere Daten |
Timetable: 1st part via MS Teams: May 20, 2026 (11am to 12am)
2nd part in person: June 8-12, 2026 (9am to 4pm) |
| Inhalt |
Course description:
The course will be a block lecture including tutorials and student presentations. The course covers a selection of state-of-the-art methods in econometrics and machine learning. It aims to provide students with a sound understanding of the methods discussed, such that they are able to do research using modern econometric techniques, as well as critically assess existing studies.
In particular, the course will cover the following topics:
• Lecture 1 & 2: OLS and 2SLS (Recap)
• Lecture 3: Regression Shrinkage Methods, Decision Trees and Random Forests, DML
• Lecture 4: Lasso and Invalid IVs (Application: Mendelian randomization)
• Lecture 5: Causal Forests (Application: Heterogenous Effects of Poverty on Cognition)
• Lecture 6: Deep Learning (Application: Fraud Detection in Claims Management)
In lecture 1 I will briefly recap the basics in OLS and 2SLS. If you have already heard about these methods, feel free to arrive on Monday at 11am.
Project Work: In these slots you are supposed to work on your application. I will be available for individual questions and discussions.
Papers you should read (potential project applications):
• Angrist and Frandsen (2022): Machine Labor, Journal of Labor Economics, 40(S1), S97–S140.
• Bach et al. (2022): DoubleML - An Object-Oriented Implementation of Double Machine Learning in Python, Journal of Machine Learning Research 23(53), 1-6.
• Borgschulte and Vogler (2020): Did the ACA Medicaid Expansion Save Lives?, Journal of Health Economics, 72, 102333.
• Brot-Goldberg et al. (2017): What does a Deductible Do? The Impact of Cost-Sharing on Health Care Prices, Quantities, and Spending Dynamics, Quarterly Journal of Economics, 132(3), 1261–1318.
• Buchner, Wasem and Schillo (2017): Regression Trees Identify Relevant Interactions: Can this Im-prove the Predictive Performance of Risk Adjustment?, Health Economics, 26, 74–85.
• Everding and Marcus (2020): The Effect of Unemployment on the Smoking Behavior of Couples, Health Economics, 154–170.
• Farbmacher, Guber, Klaassen (2022): Instrument Validity Tests with Causal Forests, Journal of Busi-ness and Economic Statistics, 40(2), 605–614.
• Farbmacher, Löw, Spindler (2022): An Explainable Attention Network for Fraud Detection in Claims Management, Journal of Econometrics, 228(2), 244–258.
• McGuire, Zink and Rose (2021): Improving the Performance of Risk Adjustment Systems, American Journal of Health Economics, 7(4).
• Rose (2016): A Machine Learning Framework for Plan Payment Risk Adjustment, Health Services Research, 51(6), 2358–2374.
• Rose, Bergquist and Layton (2017): Computational Health Economics for Identification of Unprofita-ble Health Care Enrollees, Biostatistics, 18(4), 682–694.
• Tibshirani (1996): Regression Shrinkage and Selection via the Lasso. Journal of the Royal Statistical ociety: Series B (Methodological) 58(1), 267–288.
• Windmeijer, Farbmacher, Davies, Davey Smith (2019): On the Use of the Lasso for Instrumental Variables Estimation with Some Invalid Instruments, Journal of the American Statistical Association, 114(527), 1339–1350.
• Zou (2006): The Adaptive Lasso and Its Oracle Properties, Journal of the American Statistical Asso-ciation 101(476), 1418-1429.
|
| Lernziele |
In particular, the course will likely cover the following topics:
• Regression Shrinkage Methods (Ridge, Lasso, Elastic Net)
• Decision Trees, Random/Causal Forests
• Advanced Identification Strategies (e.g., Double Machine Learning)
• Introduction to Neural Networks |
| Voraussetzungen |
A solid introductory course in econometrics. Preferably some basic knowledge of R and Python. Participants should bring their own laptop with R and/or Python installed. The target audience are PhD students. |
| Sprache |
Englisch |
| Anmeldung |
https://sggoe.ch/course-list.html |
| Leistungsnachweis |
Successful participation |
| Abschlussform / Credits |
Aktive Teilnahme (Referat) / 3 Credits
|
| Hinweise |
The course covers a selection of state-of-the-art methods in econometrics and machine
learning. It aims to provide students with a sound understanding of the methods discussed, such that they are able to do research using modern econometric techniques, as well as critically assess existing studies. |
| Hörer-/innen |
Nein |
| Kontakt |
Prof. Dr. Stefan Boes, stefan.boes@unilu.ch |
| Material |
• Goodfellow Ian, Bengio Yoshua and Courville Aaron. Deep Learning, MIT Press, available here
• Bishop Christopher. Pattern Recognition and Machine Learning, Springer, available here
• Hansen Bruce. Econometrics, available here
• Hastie Trevor, Tibshirani Robert and Friedman Jerome. The Elements of Statistical Learning, Sprin-ger, available here
• James Gareth, Witten Daniela, Hastie Trevor and Tibshirani Robert. An Introduction to Statistical Learning with Applications in R, Springer |