Ingo Rohlfing

Better get your paper submissions in for the @epssnet.bsky.social conference in June 2026, as the deadline is 7 November, and we have no intention of extended that (given the submission numbers)!
epssnet.org/belfast-2026...

A useful discussion tool is: At what point would you expect your peers (or whoever your target audience might be, such as members of the public) to throw rotten tomatoes at you for bragging about your tiny effect size? At what point would you be embarrassed?

So gehen alle beschädigt aus dem Verfahren - Projektbeteiligte und Ministerium - und es wird dem Projekt immer nachhängen, egal, wie es umgesetzt wird und was die Ergebnisse sind. 2/

Trotz Kritik: Forschungsministerium fördert umstrittenes Projekt gegen Antisemitismus - correctiv.org
correctiv.org/aktuelles/in...
Das Ministerium hat u.a. ein "conditional accept" ausgesprochen, bevor es die externe Zweitbegutachtung gab und die Bewilligung gegen Bedenken durchgezogen. 1/

There still seems to be a lot of confusion about significance testing in psych. No, p-values *don’t* become useless at large N. This flawed point also used to be framed as "too much power". But power isn't the problem – it's 1) unbalanced error rates and 2) the (lack of a) SESOI. 1/ >

🚨 Job alert! 🚨
(English in comment)

An meinem Lehrbereich ist zum 1.2.26 eine Postdoc-Stelle (100%) zu besetzen. Gesucht wird ein*e Kandidat*in mit Kenntnissen in quantitativen Methoden sowie Expertise in einschlägigen Themenbereichen. Mehr hier: www.verwaltung.uni-halle.de/dezern3/Auss...

{DAGassist} let's you process a DAG and estimate models giving {dagitty} input and baseline model #CausalSky #rstats
cran.r-project.org/web/packages... I think {ggdag} has more to offer for analysis of a DAG, while {DAGassist} is a one-stop package for classifying variables and getting estimates

Trotz Kritik: Forschungsministerium fördert umstrittenes Projekt gegen Antisemitismus Forschungsministerium fördert Antisemitismus-Projekt unter Ahmad Mansour – internen Zweifel an Wissenschaftlichkeit zu Trotz.

Das #Forschungsministerium fördert seit Juli 2025 ein Projekt gegen #Antisemitismus an Schulen – geleitet vom #Islamismus-Experten Ahmad Mansour. CORRECTIV liegen Unterlagen vor, die auf die Verletzung von wissenschaftlichen Standards hindeuten.

Check out or new article — published today in @poppublicsphere.bsky.social — where we discuss and provide guidelines for the construction and use of datasets.

We draw on our lessons from three major data collection efforts on education policies and systems 👇

Working papers
- must be complemented by code, data and documentation, where possible;
- are verified for computational reproducibility.
Experience suggests this is warranted because four papers out of five were not fully up to the standards 2/

The World Bank’s Reproducible Research Initiative: Raising the Bar for Transparency in Development Economics
www.bitss.org/the-world-ba... #OpenScience Laudable. World Bank steps up its game. 1/

CamPoS (Cambridge Philosophy of Science seminar series) is now on Bluesky! Please see our upcoming talks here: www.hps.cam.ac.uk/news-events/...

A "methods primer" article in the journal "BMJ Medicine", titled "Factors associated with: problems of using exploratory multivariable regression to identify causal risk factors"

We wrote an article explaining why you shouldn't put several variables into a regression model and report which are statistically significant - even as exploratory research. bmjmedicine.bmj.com/content/4/1/.... How did we do?

Absolut nachvollziehbar. Es ist schwer, sich mit einem Standort zu identifizieren, wenn das Ende ohnehin absehbar ist und man das regelmäßg vermittelt bekommt. Und wenn einem aus diesem Grund Aufgaben nicht anvertraut werden, weil man es nicht darf oder soll. (z.B. Mitwirkung in bestimmten Gremien)

Wichtiger Newsletter, danke Amrei. ❤️‍🩹

Ohne das zu einem "Ich-Ding" machen zu wollen: mein spontaner Gedanke war: ich kenne dieses Abschied-Gefühl irgendwie 'andersherum', weil ich an den Unis, wo ich angestellt war, gar keine Chance hatte, richtig anzukommen. Abschiede waren seltsam "dumpf" bisher.

in my post-academic era i have become extremely scathing of the way academia considers papers to the primary outcome of intellectual work, and refuses to give credit to academics who write software or build other tooling. in industry we very rarely read your papers; but we always use your software

Nature Reviews Psychology encourages authors to submit citation diversity statements #ScientificPublishing
www.nature.com/articles/s44...
It is meant as a nudge to review fields thoroughly and not to cite the "usual suspects" that have been cited since the ages

„Was, wenn es nicht reicht?“: der Satz, der mein Berufsleben seit bald 1 1/2 Jahrzehnten prägt. „Es“ steht dabei für Drittmittel, Publikationen, Arbeitsstunden, Leistung, Commitment, gebrachte Opfer uvm. Immer schwebt über allem die Angst, dass es nicht genügt. Egal, wie viel es ist. #IchBinHanna

Title: A Justification for 80% Power Abstract: Cohen’s heuristic reason for choosing 80% power (balancing Type I and TypeII errors) conveniently arrives at approximately the same number as an approachwhere one maximizes the marginal gain in power per standard error reduction. Ihave yet to see someone point this out, and this is interesting because it providesa non-arbitrary justification for 80% power.

a derivation of the result

I think this is kind of neat and I don't think anyone else has noticed it (I've looked and I can't find anyone who has) osf.io/preprints/so...

Maybe I should back off "justification" language, but it's at least a remarkable coincidence. I still think someone else *must* have noticed it...

we're hiring assistant professor in computational social science, applications close 26/10/2025

Don't forget to submit your Assistant Professor in Computational Social Science application this weekend❗

📚 jobs.lse.ac.uk/Vacancies/W/...

Applications close 26 October 🚨

Relationship between age (x-axis) and percentage of people wearing glasses (y-axis). At this setting, the chart only displays a declining trend for age 59 to 60.

Relationship between age (x-axis) and percentage of people wearing glasses (y-axis). At this setting, the chart displays age from 18 to 85 with an upward trend from 40% to about 80%.

Defense Against Dishonest Charts
flowingdata.com/projects/dis... #dataviz A highly instructive interactive guide on how charts can be deceiving and what to watch out for to avoid misinterpretation.

We have just advertised a Full Prof position in the Political and Social Sciences department at the EUI (@eui-sps.bsky.social). Here are the details. Please spread the word, and get in touch if you have any questions.
www.eui.eu/Documents/Se...

Nature asked: "Is academic research becoming too competitive?"
www.nature.com/articles/d41...
I guess this question is definitely settled for some funding schemes in the UK

“Multiverse analyses require thorough, theory-based model selection. Otherwise, they become a ‘dangerous tool’ that drowns valid models in misspecified ones, needlessly eroding trust in science.”

A plea for thoughtful models by @kauspurg.bsky.social

#MetaSci

FAIRness differed mainly by repository, with GitHub and OSF showing lower median scores than PsychArchives, Zenodo, and Figshare

How FAIR is shared data in psychology?

We analyzed 11,384 datasets (2013–2024): They're findable, but less reusable!

What relates most to differences in FAIRness? #Repository choice.

👉 Preprint: doi.org/10.23668/psy...

@mariogollwitzer.bsky.social @kaisassenberg.bsky.social #metascience #SciSci

Exploring the Potential of Large Language Models in Generating Saturated DAGs for Causal Inference | by @lucystats.bsky.social
www.lucymcgowan.com/talk/idwsds_... Very insightful. Recommendation is to combine expert input and refinement with LLMs for producing DAGs

"Many fields have come up with their own creative ways of making causal claims while maintaining plausible deniability" - @dingdingpeng.the100.ci summarises the problem before offering her tips on how to help bring rigorous causal inference methods into mainstream research!

If I understood it correctly, the effects of GenAI-adoption are small for both outcomes. Maybe they are larger now because LLMs and prompting got more advanced. 3/

- Productivity is measured through number of articles, quality throught impact factor. I may be preaching to the choir, but these are not the best and most interesting definitions.
- Focus is only on academic writing, focusing on markers of GenAI-based writing. No insights on coding, for example.
2/

Can GenAI Improve Academic Performance? Evidence from the Social and Behavioral Sciences
arxiv.org/abs/2510.02408
Interesting finding, potentially, that GenAI improves inclusiveness because it can mitigate language barriers.
Others can judge identification strategy than I, so some other points:
1/