Sign in

Michael Knaus

@mcknaus.bsky.social
498 followers 314 following 58 posts

Assistant Professor of "Data Science in Economics" at Uni Tübingen. Interested in the intersection of causal inference and so-called machine learning. Teaching material: github.com/MCKnaus/causalML-teaching Homepage: mcknaus.github.io

PostsRepliesMedia
Reposted by Michael Knaus
ML for Science @ml4science.bsky.social · 16/06/2026
We are recruiting several Early Career Research Group Leaders for Machine Learning in Science (m/f/d; E14 TV-L, 100%) in Tübingen! Open to researchers directly after their PhD or with postdoctoral experience. Application deadline: July 15, 2026. More info: uni-tuebingen.de/en/128980#c2... 1/2
Image with the text: Open Positions: Early Career Research Group Leaders for Machine Learning in Science (m/f/d, E14 TV-L, 100%). Application Deadline: July 15, 2026.
12016
Reposted by Michael Knaus
Paul Hünermund @p-hunermund.com · 22/05/2026
📆 One week left to apply! We are still looking for excellent PhD students and postdocs to join us at the TUM Heilbronn Data Science Center (HDSC).
067
Michael Knaus @mcknaus.bsky.social · 12/05/2026
@paulgp.com Maybe our primer helps: mcknaus.github.io/assets/pdfs/... (it was prepared using your Claude pipeline ;-)) After all, is there an easy way to think about time-varying covariates? E.g. is Appendix D in Ghanem/Sant'Anna/Wüthrich for T=2 less complicated? arxiv.org/abs/2203.09001
mcknaus.github.io
040
Reposted by Michael Knaus
Paul Hünermund @p-hunermund.com · 04/05/2026
🏁 We’re hiring at the TUM Heilbronn Data Science Center (PhD & Postdoc). Focus: econometrics, innovation policy, and technology management—with a particular interest in the societal and managerial implications of #causalAI. Join a highly interdisciplinary, research-driven environment at TUM. 👇
academics.de
3 PhD Positions in Empirical Economics & Data Science - Technische Universität München (TUM)
Technische Universität München (TUM) bietet Stelle als 3 PhD Positions in Empirical Economics & Data Science in Heilbronn - jetzt bewerben!
04224
Michael Knaus @mcknaus.bsky.social · 16/04/2026
Correction: ΔY1 _||_ D | X0,X1
000
Michael Knaus @mcknaus.bsky.social · 16/04/2026
@andrew.heiss.phd it is maybe too late and uses SWIGs rather than DAGs, but it speaks to your question raised here bsky.app/profile/andr...
040
Michael Knaus @mcknaus.bsky.social · 16/04/2026
For the proof that we are allowed to do all that, practical recommendations and much more, see the paper arxiv.org/abs/2604.12818 Comments are very welcome!
arxiv.org
Causal Graphs for Conditional Parallel Trends
Difference-in-Differences (DiD) is a widely used research design that often relies on a conditional parallel trends (CPT) assumption. In contrast to settings with unconfoundedness, where causal graphs...
151
Michael Knaus @mcknaus.bsky.social · 16/04/2026
(iv) with treatment–covariate feedback, all dynamic effect estimates are biased, reflecting omitted variable bias or “wrong world control bias” (v) pre-trends do not diagnose post-treatment violations of CPT, while short-term effects can remain unbiased even with treatment–covariate feedback.
120
Michael Knaus @mcknaus.bsky.social · 16/04/2026
(i) pre-treatment covariates yield parallel pre-trends and unbiased short-term effects but biased dynamic effects (ii) pre-outcome controls provide the same results as full sequence (iii) in the absence of treatment-covariate feedback, strategies involving post-treatment variables are unbiased ...
110
Michael Knaus @mcknaus.bsky.social · 16/04/2026
We generalize to arbitrary time periods and provide a table that shows the minimal valid adjustment set under different causal structures. This contains some useful insights that we illustrate in a simulation 👇
120
Michael Knaus @mcknaus.bsky.social · 16/04/2026
With three periods, graphs become more messy and independencies must be stichted together, but provide interesting insights. If time Xt -> Dt, but Dt -> Xt+1, short term effects are identified, but dynamic effects not.
120
Michael Knaus @mcknaus.bsky.social · 16/04/2026
We illustrate why outcome dynamics rule out PT, unless more restrictions are imposed. Y0 becomes a dilemma node that can only block one of two open paths between D and ΔYt
140
Michael Knaus @mcknaus.bsky.social · 16/04/2026
Δ-SWIGs are transformed Single World Intervention Graphs, which are themselves transformed DAGs. Good news: d-separation is all you need => path-blocking skills from DAGs apply. E.g. ΔYt _||_ D | X1,X2 such that PT E[ΔYt | D=1, X1,X2] = E[ΔYt | D=0, X1,X2] holds Also, conditioning on Y0 => M-bias
220
Michael Knaus @mcknaus.bsky.social · 16/04/2026
NEW PAPER 🚨 "Causal Graphs for Conditional Parallel Trends" with @henripf.bsky.social It connects causal graphs and the modern Diff-in-Diff literature by introducing Δ-SWIGs as a graphical tool to reason about controls in DiD settings under standard additively separability assumptions. Thread 🧵
1279
Reposted by Michael Knaus
Ulrike Luxburg @ulrikeluxburg.bsky.social · 17/09/2025
I am hiring PhD students and/or Postdocs, to work on the theory of explainable machine learning. Please apply through Ellis or IMPRS, deadlines end october/mid november. In particular: Women, where are you? Our community needs you!!! imprs.is.mpg.de/application ellis.eu/news/ellis-p...
02415
Michael Knaus @mcknaus.bsky.social · 12/09/2025
🚨Job alert🚨 Premium tenure-track (ass to full prof) in "𝐌𝐋 𝐌𝐞𝐭𝐡𝐨𝐝𝐬 𝐢𝐧 𝐁𝐮𝐬𝐢𝐧𝐞𝐬𝐬 𝐚𝐧𝐝 𝐄𝐜𝐨𝐧𝐨𝐦𝐢𝐜𝐬" @unituebingen.bsky.social made possible by @ml4science.bsky.social Spread the word and feel free to reach out if you have any questions about the position or the environment. Link: shorturl.at/QHZ5G
031
Michael Knaus @mcknaus.bsky.social · 30/05/2025
Me too 😄 I just pitched a vague idea to my research/art assistant and he came back with this.
000
Michael Knaus @mcknaus.bsky.social · 28/05/2025
The OutcomeWeights #RStats package now has a logo and a new vignette illustrating how Double ML improves covariate balance over "Single ML" RA or IPW. Check it out: mcknaus.github.io/OutcomeWeigh... #causalSky #causalML
140
Reposted by Michael Knaus
Dominika Langenmayr @dlangenmayr.bsky.social · 22/05/2025
Wir suchen jemanden, der im WS 25/26 unseren vakanten Lehrstuhl für Statistik und Quantitative Methoden in den Wirtschaftswissenschaften vertritt. Auch die Dauerstelle wird bald ausgeschrieben. Wir freuen uns über nette, engagierte Kollegen! Gerne teilen... Link im nächsten Post.
166
Reposted by Michael Knaus
Ulrike Luxburg @ulrikeluxburg.bsky.social · 23/05/2025
Our cluster Machine Learning for Science is up for 7 years more funding!
0245
Michael Knaus @mcknaus.bsky.social · 23/05/2025
Excellent news! The "Machine Learning for Science" cluster is an incredible public good for researchers @unituebingen.bsky.social interested in ML in all its facets. Great job by @philipp.hertie.ai, @ulrikeluxburg.bsky.social and the cluster team.
030
Reposted by Michael Knaus
ML for Science @ml4science.bsky.social · 22/05/2025
We're super happy: Our Cluster of Excellence will continue to receive funding from the German Research Foundation @dfg.de ! Here’s to 7 more years of exciting research at the intersection of #machinelearning and science! Find out more: uni-tuebingen.de/en/research/... #ExcellenceStrategy
The members of the Cluster of Excellence "Machine Learning: New Perspectives for Science" raise their glasses and celebrate securing another funding period.
47520
Reposted by Michael Knaus
INOMICS @inomics.bsky.social · 13/05/2025
Junior Professorship (W1) with tenure track (W3) in Statistics and Empirical Economics #Econsky
dlvr.it
Junior Professorship (W1) with tenure track (W3) in Statistics and Empirical Economics
The future job holder shall be responsible for the subject area Statistics and Empirical Economics with a methodological focus in research and teaching. The professorship offers central courses in the field of statistics, empirical economics, and statistical data science in both the German-language Bachelor and English-language Master programs of the Faculty of Business, Economics and Social Sciences. Active participation in the Faculty's PhD program and in the…
012
Reposted by Michael Knaus
Bruno Ferman @brunoferman.bsky.social · 29/04/2025
🧵New survey paper: "Inference with Few Treated Units" Luis Alvarez, Bruno Ferman and Kaspar Wüthrich Tired of referees saying your standard errors are wrong? This survey will help you understand if you really have a problem — and, if so, how to fix it!
15714
Reposted by Michael Knaus
Michael Knaus @mcknaus.bsky.social · 25/04/2025
One of my favorite parts is running OLS within the DoubleML package of @philippbach.bsky.social and colleagues. Of course this is unnecessarily complicated, but instructive.
111
Reposted by Michael Knaus
Econometrica @ecmaeditors.bsky.social · 25/04/2025
How can we design algorithms that maximize social welfare, rather than profits? This paper merges multi-armed bandits and adversarial learning with optimal tax theory and welfare economics. @maxkasy @NicoloCB @Rcolomboni buff.ly/pxPY8nj
0269
Michael Knaus @mcknaus.bsky.social · 25/04/2025
@dariia.bsky.social
020
Michael Knaus @mcknaus.bsky.social · 25/04/2025
If you find this interesting and want the recording of the session, you can still get access for a donation via sites.google.com/view/dariia-...
sites.google.com
Dariia Mykhailyshyna - Workshops for Ukraine
Feedback on the past workshops (if you want to learn how to make wordclouds, check out Text Data Analysis workshop below)
110
Michael Knaus @mcknaus.bsky.social · 25/04/2025
One of my favorite parts is running OLS within the DoubleML package of @philippbach.bsky.social and colleagues. Of course this is unnecessarily complicated, but instructive.
111
Michael Knaus @mcknaus.bsky.social · 25/04/2025
One year ago I gave a #CausalML Workshop for Ukraine 🇺🇦 We hand-coded DoubleML and causal forest in very few lines of code to exactly replicate their package outputs. If you better understand theory through coding like me, check it out. You find the R notebook now online: shorturl.at/uM82n #RStats
shorturl.at
Introduction to Causal ML estimators in R
1121
Reposted by Michael Knaus
Maximilian Kasy @maxkasy.bsky.social · 24/04/2025
🤖 Interested in machine learning, economics, and the state of AI?🤖 In September, I will teach a 1-week intensive version of my course on foundations of ML (maxkasy.github.io/home/ML_Oxfo...) in our summer school. Apply here: ouess.web.ox.ac.uk/september-su... Spread the word!
maxkasy.github.io
Foundations of Machine Learning
Research on machine learning, experimental design, economic inequality, and optimal policy
01811
Michael Knaus @mcknaus.bsky.social · 25/03/2025
I am a fan of this one, though it is not diverging but converging: doi.org/10.1016/j.ec... It is so obvious where the policy change happens that it is not even indicated...
010
Reposted by Michael Knaus
Jaap Abbring @jaap.abbring.org · 20/03/2025
#EctJ published a SI celebrating the seminal contributions of Philip G. Wright to causal inference in economics. Both our editorial & reproduction of Wright (1928) are free to read. @resmedia.bsky.social @p-hunermund.com @borusyak.bsky.social @instrumenthull.bsky.social res.org.uk/celebrating-...
res.org.uk
Celebrating Philip G. Wright’s legacy: directed acyclic graphs and instrumental variables - Royal Economic Society
The Econometrics Journal published a special issue celebrating the seminal contributions of Philip G. Wright (1928).
0139
Reposted by Michael Knaus
Paul Goldsmith-Pinkham @paulgp.com · 19/03/2025
Interesting new paper: arxiv.org/pdf/2503.09907 improves on both rdrobust and rdhonest! Quite compelling... 1/n
413537
Reposted by Michael Knaus
Juan Moreno-Cruz @jmorenocruz.bsky.social · 18/03/2025
It’s finally out! People, I’ve been hearing about this paper for so many years, but I am grateful it is out. Andrew Baker, Brantly Callaway, Scott Cunningham, Andrew Goodman-Bacon, Pedro H. C. Sant’Anna www.linkedin.com/posts/andrew... arxiv.org/abs/2503.13323
arxiv.org
Difference-in-Differences Designs: A Practitioner's Guide
Difference-in-Differences (DiD) is arguably the most popular quasi-experimental research design. Its canonical form, with two groups and two periods, is well-understood. However, empirical practices c...
011127
Reposted by Michael Knaus
Vladislav Morozov @vladislavmorozov.bsky.social · 18/03/2025
Just uploaded the first block of my lecture notes on econometrics with unobserved heterogeneity! 📊 Introduction and a block on average effects in linear models with heterogeneous coefficients — why standard estimators fail and a robust approach. Link below. #econsky
161
Reposted by Michael Knaus
Achim Zeileis @zeileis.org · 10/03/2025
Our dept/faculty @uniinnsbruck@social.uibk.ac.at is looking for a senior scientist - to coordinate a new master program - to teach statistics & data science in that master (and beyond) German skills needed. Further details & online application at: lfuonline.uibk.ac.at/public/karri...
Screenshot of the job offer online at https://lfuonline.uibk.ac.at/public/karriereportal.details?asg_id_in=14873
087
Reposted by Michael Knaus
Georg Weizsäcker @georgweizsaecker.bsky.social · 09/03/2025
Among the many good things about support for 🇺🇦: Doing it together This coordination of donations is open until tomorrow 10am CET 👇 and support via any other channel is equally good, too.
12418
Reposted by Michael Knaus
csteinwender.bsky.social @csteinwender.bsky.social · 06/03/2025
we are looking for an Associate Professor (tenure track) in applied Economics, pls share: www.timeshighereducation.com/unijobs/list...
timeshighereducation.com
Professorship (W2) of AI in Economics - Munich (City), Bavaria, Germany job with LUDWIG MAXIMILIANS UNIVERSITAET MUENCHEN | 389325
All AI that are relevant to the field of economics under the application of modern statistical methods will be expected to teach courses at all levels
01214
Reposted by Michael Knaus
Elliott Ash @elliottash.bsky.social · 28/02/2025
📣Now hiring: Predoc in Economics and Data Science We are hiring a predoc -- work at ETH Zurich on exciting projects in applied econ (political econ, education, etc.), using AI, NLP, and causal inference. Apply here: econjobmarket.org/positions/11505
econjobmarket.org
EJM - Econ Job Market
01512
Reposted by Michael Knaus
Centre for Research in Economics and Statistics (UMR 9194) @crestumr.bsky.social · 17/02/2025
🚀 Call for Papers: CREST-IFAU Workshop on Labor Market Policy Evaluation 📊 🗓 June 12-13, 2025 – Paris (Palaiseau) 🎤 Keynote: Stéphane Bonhomme (University of Chicago) 📅 Submit by: March 10, 2025 📩 Send papers (PDF) to: workshops@ensae.fr @ifau.bsky.social
crest.science
Call for papers: CREST – IFAU Workshop on Evaluating Labor Market Policies: Methods and Results - CREST
0117
Reposted by Michael Knaus
Wieland Brendel @wielandbrendel.bsky.social · 11/02/2025
🚀 We’re hiring! Join Bernhard Schölkopf & me at @ellisinsttue.bsky.social to push the frontier of #AI in education! We’re building cutting-edge, open-source AI tutoring models for high-quality, adaptive learning for all pupils with support from the Hector Foundation. 👉 forms.gle/sxvXbJhZSccr...
Hiring announcement: ELLIS Institute Tübingen is looking for ML Researchers & Engineers for Open-Source AI Tutoring (m/f/d). The image features a white background with bold black text and the colorful ELLIS logo at the bottom.
1914
Reposted by Michael Knaus
Vladislav Morozov @vladislavmorozov.bsky.social · 03/02/2025
Adding fixed effects is supposed to reduce bias — but under realistic parameter heterogeneity, it can make bias worse I wrote a post explaining how and why this can happen, with simulations and what you can do about it (Video: results summary) Links to post and Python code in replies #EconSky
1194
Reposted by Michael Knaus
Giovanni Mellace @giovannimellace.bsky.social · 30/01/2025
We’re looking for a motivated researcher to apply for a Marie Skłodowska-Curie postdoc with our Econometrics & Data Science group at SDU! Focus: Causal Inference, Machine Learning, Big Data Full support for promising projects More info & apply: www.sdu.dk/en/om-sdu/in...
sdu.dk
Econometrics and Data Science
01812
Reposted by Michael Knaus
Pedro Sant’Anna @pedrosantanna.bsky.social · 22/01/2025
To continue the public good streak, here are some cool materials that our @emoryeconomics.bsky.social student, Marcelo Ortiz-Villavicencio, prepared for his independent studies. marcelortiz.com/ECON697R/ I am biased, but the slides are clear and relevant to many econometrics topics.
marcelortiz.com
Topics in High-Dimensional Econometrics and ML Theory
A modern, highly customizable, responsive Jekyll template for course websites
25513
Reposted by Michael Knaus
JungHo Lee @jungholee.bsky.social · 17/01/2025
Excited to share a new paper on ML-assisted randomization tests for detecting various treatment effects!
071
Reposted by Michael Knaus
Clément de Chaisemartin @cdechaisemartin.bsky.social · 16/01/2025
Are you estimating a first-difference (FD) regression, assuming that treatment changes randomly assigned? Happy to share new paper with two simple pieces of advice. papers.ssrn.com/sol3/papers.... Advice 1: start by regressing treatment change Delta D on baseline treatment D1.
1263
Reposted by Michael Knaus
Grant McDermott @gmcd.bsky.social · 16/01/2025
A while coming, but happy to say that `parttree` is finally on CRAN. #rstats #dataviz Visualize simple decision tree partitions on the scale of the data. Useful for getting an intuitive sense of how your model has carved up the feature space. Works for both classification & regression tasks. 1/2
Example of a classification tree partition.Example of a regression tree partition.
34314
Michael Knaus @mcknaus.bsky.social · 16/01/2025
@maxkasy.bsky.social uses POs in his bandit and reinforcement learning slides here maxkasy.github.io/home/ML_Oxfo...
maxkasy.github.io
Foundations of Machine Learning
Research on machine learning, experimental design, economic inequality, and optimal policy
0114