iiinova — where your digital self keeps evolving

Dominik Liebl @dliebl.com · 22/01/2026

@ccfang819.bsky.social my PhD student @unibonn.bsky.social and coauthor of the below 👇 paper is now also here at bsky. Follow recommendation 😉

010

Dominik Liebl @dliebl.com · 21/01/2026

Honest causal inference accounts for this bias by testing effects against an honest reference band (zero ± bias). Our contribution: We make event-study plots honest using simultaneous confidence bands (SCBs). 🤓 We use infimum- and supremum-based SCB!

arxiv.org

Making Event Study Plots Honest: A Functional Data Approach to Causal Inference

Event study plots are the centerpiece of Difference-in-Differences (DiD) analysis, but current plotting methods cannot provide honest causal inference when the parallel trends and/or no-anticipation a...

120

Dominik Liebl @dliebl.com · 21/01/2026

Event-study plots in DiD are incredibly persuasive—but, honestly, not always honest. Why? If parallel trends or no anticipation fail, DiD estimates are biased. Testing against a zero-effect null then becomes misleading. 🚨New 📄: arxiv.org/abs/2512.06804 #CausalInference #EconSky #StatsSky #rstats

195

Reposted by Dominik Liebl

Achim Zeileis @zeileis.org · 13/12/2025

These are the materials for our 1-semester course Introduction to Programming with R It's geared towards 1st-year bachelor students without any prior programming experience. #rstats discdown.org/rprogramming/

discdown.org

2101

Reposted by Dominik Liebl

arXiv econ.EM Econometrics @econem-bot.bsky.social · 09/12/2025

Chencheng Fang, Dominik Liebl: Making Event Study Plots Honest: A Functional Data Approach to Causal Inference arxiv.org/abs/2512.06804 arxiv.org/pdf/2512.06804 arxiv.org/html/2512.06804

021

Reposted by Dominik Liebl

Open Science @UniBonn @opensciene-unibonn.bsky.social · 25/08/2025

👋 Our first post! We are the #ResearchData & #OpenAccess Service Centers at @unibonn.bsky.social. We: 📖 fund OA publications 📝 consult & train on data management 🎓 offer tools for processing & sharing research data We'll share insights, resources & updates from our work! #OpenScience #UniBonn

052

Reposted by Dominik Liebl

Ming Tommy Tang @tommytang.bsky.social · 17/08/2025

Applied HPC with R book-hpc.ggvy.cl/ #rstats

0189

Reposted by Dominik Liebl

Amstat-American Statistical Association @amstatnews.bsky.social · 11/08/2025

StatFest 2025 is here and it's free and virtual. Undergrad students from historically underrepresented groups connect with industry experts in statistics, data science, and academia. Sept. 11, 18, & 25. Register today. community.amstat.org... #StatFest2025 #DataScience #Statistics #STEMCareers

"Register now" with an image of a megaphone

043

Reposted by Dominik Liebl

Khoa @khoavuumn.bsky.social · 14/07/2025

Using time series graphs to make causal claims be like

11847159

Reposted by Dominik Liebl

Universität Bonn @unibonn.bsky.social · 08/07/2025

🎉Congratulations to our graduates 2025! Forever Uni Bonn - Over 2,000 graduates celebrated the 20th anniversary of its Universitätsfest — with over 5,000 of their friends and family — a new record. Read more www.uni-bonn.de/en/news/20-j... (c) Marc John/Uni Bonn #UniversityOfBonn #ForeverUniBonn

Group photo: graduates celebrated the 20th anniversary of ist Universitätsfest in the Hofgarten.

0123

Reposted by Dominik Liebl

Dariia Mykhailyshyna @dariia.bsky.social · 04/07/2025

Hi #EconSky! I will be teaching intro statistics with #rstats next academic year. Any suggestions for free learning resources for students and/or teaching materials?

113712

Dominik Liebl @dliebl.com · 04/07/2025

Nice thread on simultaneous confidence bands (SCBs) by @noahgreifer.bsky.social ! Not many papers explore varying critical values—despite cool uses like narrower or fairer bands. Bit of shameless self-promo if you're into this 😉: academic.oup.com/jrsssb/artic... #econsky #statsky

academic.oup.com

Fast and fair simultaneous confidence bands for functional parameters

Abstract. Quantifying uncertainty using confidence regions is a central goal of statistical inference. Despite this, methodologies for confidence bands in

051

Reposted by Dominik Liebl

Vincent Arel-Bundock @vincentab.bsky.social · 06/06/2025

🚨 Big milestone for Rdatasets 🚨 The web archive now hosts 3400+ free and documented CSV datasets. Fantastic for teaching and testing! And {Rdatasets} is a new #RStats 📦 for easy download and search Web archive: vincentarelbundock.github.io/Rdatasets R 📦: vincentarelbundock.github.io/Rdatasetspkg

325578

Reposted by Dominik Liebl

Dani Rodrik @drodrik.bsky.social · 17/05/2025

Just learned something new. You can buy spurious citations that will show up on Google Scholar -- and people do.

714158

Dominik Liebl @dliebl.com · 14/05/2025

New working paper: "Testing the Missing Completely at Random Assumption for Functional Data," joint work with Max Ofner*, S. Hörmann and D. Kraus. As far as we know, it's the first paper on testing MCAR for functional data. *Look out for this smart guy.

010

Dominik Liebl @dliebl.com · 04/05/2025

Grace Wahba, "the mother of smoothing splines," won the International Prize (aka the Nobel) in Statistics #stats for her representer theorem. youtu.be/8Ae_QzwwR_U?... So well deserved! I guess, one could also give her the price again in two years for her work on Generalized Cross-Validation.

06316

Reposted by Dominik Liebl

Universität Bonn @unibonn.bsky.social · 17/01/2025

Played through Sportify? We got you. Pointed and scientific - that's the #Hypothesis #Podcast from the #UniversityofBonn. Listen now: www.uni-bonn.de/de/universit... For our next episodes: Which topic would interests you the most?

051

Dominik Liebl @dliebl.com · 12/12/2024

🚨 To all scientists interested in functional data analysis: Functional Data Analysis: Workshop in Honor of Alois Kneip Date: June 12-13, 2025 Registration: Open until January 26, 2025 www.mathematics.uni-bonn.de/hcm/events/w... Pls help spread the word. 🙏

Figure contains a qr-code to the homepage of the workshop:
https://www.mathematics.uni-bonn.de/hcm/events/workshops-conferences/workshop_functional-data-analysis-a

081

Reposted by Dominik Liebl

λ³🎲 @cubiclogic.bsky.social · 20/10/2023

You may have all see this as an example of survivorship bias #MathSky

3174

Dominik Liebl @dliebl.com · 18/10/2023

You puzzled me with this plot. My first thought was that it doesn't really look like the condition mean of Y | X=x, Group=blue. 2nd thought: No! Paul is doing it right, for sure. Finally, "Sherlock"-me found the missing blue dots behind the black ones. 🕵️

120

Reposted by Dominik Liebl

Data Colada @datacolada.bsky.social · 11/10/2023

Hello world

28123

Dominik Liebl @dliebl.com · 11/10/2023

Freue mich auch. Wollte Roland und die ganze Gruppe schon lange mal besuchen.

000

Dominik Liebl @dliebl.com · 10/10/2023

"I have a feeling he is deceiving himself." (I know it's old, but it's such a beautiful short story.) #statssky #econsky stats.stackexchange.com/questions/18...

0103

Reposted by Dominik Liebl

Simon Jäger @simonjaeger.bsky.social · 09/10/2023

Riesige Glückwünsche an Claudia Goldin zum diesjährigen Nobelpreis für Wirtschaftswissenschaften! Worum geht es bei ihrer Forschung? Ein paar Eindrücke aus ihrer Forschung zum Arbeitsmarkt (auf deutsch).

110645

Reposted by Dominik Liebl

Patrick Schneider @pschneider.bsky.social · 09/10/2023

There is a new feature to show some posts from other feeds in your following feed. 📈📉

0102

Reposted by Dominik Liebl

Allison Horst @allisonhorst.bsky.social · 23/08/2023

Teaching intro data science or stats in environmental sciences / ecology this fall? The lterdatasampler package is now on CRAN, with curated real world datasets from the US Long Term Ecological Research program! Check it out: lter.github.io/lterdatasamp...

A hexagonal design with the words lterdatasampler at the top. Within the border are plants, animals and weather patterns representing the different datasets currently in the package.

310143

Dominik Liebl @dliebl.com · 06/10/2023

Missing the metrics community too. @zeileis.org is here. Some folks from the biostats community are here under #statsky

130

Reposted by Dominik Liebl

Sven Otto @svenotto.com · 06/10/2023

I recently experimented with Quarto, the next-gen rmarkdown. It can be used to produce wonderful online lecture sites combining theory with R code. This is a refresher in matrix algebra for my econometrics students: matrix.svenotto.com

matrix.svenotto.com

Crash Course in Matrix Algebra

A Refresher on Matrix Algebra for Econometricians with Implementation in R

061

Reposted by Dominik Liebl

Iris van Rooij 💭 @irisvanrooij.bsky.social · 05/10/2023

Why do academics throw all scientific standards out of the window as soon as the topic is “AI”?

69316

Reposted by Dominik Liebl

Connair J. S. Russell @connairrussell.bsky.social · 28/09/2023

Groundhog for R is so good for reproducibility. You just load your packages with it and voila, anyone who runs your script will have the same package versions. One less hurdle to reproducible code. Props to the team at Wharton Credibility Lab! groundhogr.com #psychscisky

310442

Dominik Liebl @dliebl.com · 04/10/2023

Nice! 10 Fundamental Theorems for Econometrics and their proofs: #Econsky bookdown.org/ts_robinson1...

073

Dominik Liebl @dliebl.com · 04/10/2023

I have now my own #bsky handle that matches the web address of my homepage: @dliebl.com Works like a charm with the descriptions provided below: h/t @hannesullrich.com & @davidwalsh.name

130

Reposted by Dominik Liebl

Hannes Ullrich @hannesullrich.com · 04/10/2023

Reposting for newcomers: you can kind of self-verify on Bluesky (and have a nicer handle). #EconSky If you have a domain where you can control the DNS entries (often the case if you have a domain forwarding to or hosting your personal website), follow the quite easy instructions in the linked post:

01810

Dominik Liebl @dliebl.com · 04/10/2023

Mastering plotting in base-R: Excellent resource: github.com/karoliskonce...

010

Dominik Liebl @dliebl.com · 03/10/2023

Mein Computational Statistics Kurs in diesem Semester wird sowas wie ein montägliches Stats-Bootcamp. Im besten Fall wird es ein großer Spaß. Aber wahrscheinlich werfen sie ihre Kaffeebecher nach mir.

010

Dominik Liebl @dliebl.com · 03/10/2023

Yeah. These arguments often become too idealistic, I think. I am more a pragmatic person. Observational is dirty and the information contained is typically unclear. I like causal inference since the assumption-framework that is used to extract information is pretty clear/discussable.

010

Reposted by Dominik Liebl

Achim Zeileis @zeileis.org · 03/10/2023

New R/exams interface to "webexercises" pkg by @debruine.bsky.social & Dale Barr Embed #rexams exercises in static HTML, R/Markdown, Quarto, etc. Pkg still on R-Forge, replication code in alt text of first image. Try: www.zeileis.org/quiz.html #elearning #rstats

Screenshot of R/exams "deriv" exercise (numeric), rendered with webexercises, showing the correct answer and full solution.

Replication code for the entire quiz:

## installation of packages
install.packages("webexercises")
install.packages(c("exams", "exams2webexercises"),
repos = "https://R-Forge.R-project.org")

## render quiz
library("exams2webexercises")
ex <- list(
c("swisscapital.Rmd", "capitals.Rmd"),
"deriv.Rnw",
"deriv2.Rnw",
"fruit.Rmd",
"boxplots.Rmd",
"ttest.Rmd",
"function.Rmd",
"lm2.Rnw",
"fourfold2.Rmd"
)
render_quiz(ex)

Screenshot of R/exams "capitals" exercise (multiple-choice), rendered with webexercises, showing some correct and incorrect answers and full solution explanation.

Screenshot of R/exams "fruit" exercise (numeric with images), rendered with webexercises, showing an incorrect answer.

Screenshot of R/exams "lm2" cloze exercise with string, multiple-choice, numeric, and single-choice elements. Rendered with webexercises.

031

Dominik Liebl @dliebl.com · 02/10/2023

Freilich. Building on the shoulders... I am often deeply impressed about the impact these researchers had. (His role in eugenics does *not* belong to these impressing things.)

110

Dominik Liebl @dliebl.com · 02/10/2023

📢 We are hiring! Assistant Professorship (W1) in Econometrics (with Tenure Track) We are searching for candidates interested in doing methodological research in econometrics and/or statistics. t.co/DNFDKl9R7U

033

Dominik Liebl @dliebl.com · 02/10/2023

"Statistics is the grammar of science." (Karl Pearson) "Bad English is the language of science." (Jan de Leeuw)

151