Ingo Rohlfing

@ingorohlfing
1.3K Followers
944 Following
2.2K Posts
I am here for all interesting and funny posts on the social sciences, broadly understood, academia, teaching, research and science
ORCIDhttps://orcid.org/0000-0001-8715-4771
Linktreehttps://linktr.ee/ingorohlfing
Githubhttps://github.com/ingorohlfing
Personal websitehttps://ingorohlfing.wordpress.com/
Show threadIngo Rohlfing6h ago
I like how the instructors introduce the students to exhaustive H0 and H1 in one-sided testing. If they have positive teaching experience with this, then this is fine. After having read the article, I was not convinced that this enhances understanding of alpha and type I error over a point null value in one-sided tests because the two types of one-sided tests are very similar in the end. 2/
Ingo Rohlfing6h ago
Unraveling the Mystery of Equality in the Null Hypothesis: How Using Inequality Enhances Conceptual Understanding of Hypothesis Testing for Our Introductory Students
https://www.tandfonline.com/doi/full/10.1080/26939169.2025.2610942
That's an interesting article. I swear, this term was the first time that I wondered myself why one has the same point null value in one-sided and two-sided tests. One make sense of it, but as the article notes, H0 and H1 are exhaustive for a one-sided test. Is anyone teaching this in the social sciences? 1/
Ingo Rohlfing4d ago
TU Berlin muss weiteres Gebäude wegen Mängeln schließen
https://www.rbb24.de/panorama/beitrag/2026/06/tu-berlin-maengel-gebaeude-schliessen.html
Gebäudeschließungsdomino an der TU Berlin
TU Berlin muss weiteres Gebäude wegen Mängeln schließen

Erst musste das Hauptgebäude schließen, dann vorrübergehend eine Bibliothek - nun macht ein weiteres Gebäude der TU Berlin Probleme. Mehrere Hörsäle und Seminarräume sind betroffen.

rbb24.de
Show threadIngo RohlfingJun 10
Many-labs studies are valuable and worth doing, but one should not put misplaced hope in them being the only or best means to improve science and advance knowledge. 2/
Ingo RohlfingJun 10
Can an army of babies and dogs rescue psychology from its reproducibility crisis?
https://www.nature.com/articles/d41586-026-01727-x
No. Leaving aside how much of a crisis there is to be rescued from, the article explains why not.
1) When a many-labs study is flawed for theoretical or design reasons, it does not help to have many labs involved. It is like a crowd instead of an individual marching in the wrong direction.
2) Many-labs studies don't scale because we cannot have one for every possible research question.
1/
Can an army of babies and dogs rescue psychology from its reproducibility crisis?

Labs are teaming up to run a host of huge projects that aim to bring rigour to cognitive science.

Ingo RohlfingJun 9
Mark RubinJun 9

News about Research on Research, Open Infrastructures, Adaptive Preregistration, and Science Reform

https://open.substack.com/pub/markrubin/p/research-on-research-open-infrastructures?r=2bqjb7&utm_campaign=post-expanded-share&utm_medium=web

Research on Research, Open Infrastructures, Adaptive Preregistration, and Science Reform

.

Critical Metascience
Ingo RohlfingJun 7
Henrik BengtssonJun 6

#RStats challenge and potential community project:

* Create a minimal package 'dumpsterfire' that triggers as many 'R CMD check' issues as possible!

Fun, but could also become a excellent resource for illustrating and understanding package check issues

Here's a start: https://github.com/HenrikBengtsson/dumpsterfire

Ingo RohlfingJun 2
ORCID OrganizationJun 2

Nominations are open for ORCID Board of Directors: 👉 https://info.orcid.org/nominations-now-open-for-orcid-board-elections-2027/

+ ORCID's Researcher Advisory Council: 👉 https://info.orcid.org/calling-all-researchers-orcid-researcher-advisory-council-nominations-now-open/

📅 Nominations deadline 26 June!

Curious about what the ORCID Board does? Join us for an Ask Me Anything: The Board on 17 June:
👉 https://orcid-org.zoom.us/webinar/register/1417799084560/WN_GLatkNsyS4qbFEnxM9jdaA

Ingo RohlfingJun 2
Peer-reviewed papers are ‘old hat science’, says millionaire investor - Research Professional News
https://www.researchprofessionalnews.com/rr-news-uk-innovation-2026-6-peer-reviewed-papers-are-old-hat-science-says-millionaire-investor/
Sure, pre-publication peer review is slow and not perfect, but it remains unclear what the alternative is. Just let AI loose on all kinds of text and knowledge and let it find patterns, like described here? https://corpora.ai/ Reads a bit like hubris, again, and seeing "trillions of correlations" as something positive, as I read it, makes me very sceptical.
Ingo RohlfingMay 30
Alex WildMay 30

tl,dr; Scientists no longer allowed to use federal funding to publish, attend meetings, or talk to the public. They cannot collaborate internationally. Grants can be cancelled for any reason, at any time, political appointees have a final say over what gets funded, and who gets funded.

https://www.science.org/content/article/white-house-seeks-tighten-political-oversight-grantmaking