Ingo Rohlfing
LightNews LightNews
banner
ingorohlfing.bsky.social
Ingo Rohlfing
@ingorohlfing.bsky.social
4.4K followers 1.3K following 1.2K posts

I am here for all interesting and funny posts on the social sciences, broadly understood and including open science and meta science, academia, teaching and research. https://linktr.ee/ingorohlfing

Videos
Political science 30%
Sociology 17%
Posts Replies Media Videos

Reposted by Mark J. Brandt, Ingo Rohlfing

Andrew Gelman et al. @statmodeling.bsky.social · 1d
Concerns about the z-curve method
statmodeling.stat.columbia.edu/2026/01/10/c...
Concerns about the z-curve method | Statistical Modeling, Causal Inference, and Social Science
statmodeling.stat.columbia.edu

Reposted by Noelle E. Selin, Jesse H. Kroll, Simon J. Greenhill , and 7 more

cdelawalla.bsky.social
Colette Delawalla @cdelawalla.bsky.social · 1d
This is a HUGE win…and one that happened because we ~collectively~ said “NO!”

But AAAS coming in and saying on record to the NYT “Science is doing ok. Things are not bad at all…” is baffling.

If things are hard for you as a scientist, please share in the comments.

www.nytimes.com/2026/01/10/s...
Congress Is Reversing Trump’s Steep Budget Cuts to Science
www.nytimes.com

Reposted by Mark Rubin, Ingo Rohlfing

thehandlab.bsky.social
Nick Holmes @thehandlab.bsky.social · 2d
Working on a principled way to describe the sample size, N, in #science papers. Will be attempting to prove Holmes' theorem over the next few years. Feedback welcome 🙏 #stats
Holmes’ theorem: N is not "large" if 1. p>.05 2. p<.05 and the Result is Displeasing

ingorohlfing.bsky.social
Ingo Rohlfing @ingorohlfing.bsky.social · 3d
Ist das die Begründung? Meine erste Vermutung war, dass das Antragsvolumen zugenommen hat und dass man auch deshalb davon ausgeht, dass die Nutzung von LLMs zunimmt und man es ohnehin nicht eindämmen kann.

Reposted by Elizabeth Stokoe, Ingo Rohlfing, Johannes Breuer , and 1 more

altmetric.com
Altmetric @altmetric.com · 3d
X/Twitter's rough full volume is around 500 total million posts every day, or 182 (and a half) billion posts per year.

By contracts, we found 11.2 million research posts in all of 2025 on there.

In other words, 0.000006% of Twitter appears to be sharing research. Basically zero.

Reposted by Lisa W. Fazio, Scott L. Greer, Caroline Krafft , and 7 more

altmetric.com
Altmetric @altmetric.com · 3d
Since Jan 1 2025, which feels like four trillion years ago, research has been shared on here 5 million whole-ass times. Bluesky recently passed 2 billion posts IN TOTAL.

So 0.25% of the entire site's traffic was citations to research.

That is actually massively high. Is it? Yes. Here's why.
Altmetric Explorer screenshot: Showing 5,011,088 mentions (from 4,918,333 individual posts) of research outputs from the results of your search query.

ingorohlfing.bsky.social
Ingo Rohlfing @ingorohlfing.bsky.social · 3d
Rejections for lack of clarity likely occur more often, but I can imagine one can be writing too clearly. In the sense that the theoretical argument may read too simple in the eyes of some, or that one is too transparent about the study's limitations (some kind of Streisand effect)

Reposted by Marten Winter, Norbert Marwan, Thomas Backhaus , and 8 more

simonhammann.bsky.social
Simon Hammann @simonhammann.bsky.social · 3d
DFG erlaubt Einsatz von KI in der Begutachtung.

Wenn wir jetzt noch die AI dazu kriegen, die komplette Forschung zu machen, haben wir den Menschen komplett von der Last des Forschungsprozzeses befreit und er kann sich komplett auf wichtige Dinge wie Reisekostenerstattungsanträge konzentrieren.
Künstliche Intelligenz in der Begutachtung
www.dfg.de

ingorohlfing.bsky.social
Ingo Rohlfing @ingorohlfing.bsky.social · 4d
Sorry, should have read "article", of course, not journal

ingorohlfing.bsky.social
Ingo Rohlfing @ingorohlfing.bsky.social · 4d
For a journal of mine, I realized that the official citation on the publisher webpage conflates the year of the publication in an issue with the year of the online-first publication. I submitted a ticket two months ago asking to correct it, nothing has happened yet. Not so much added value here.

Reposted by David Lazer, Ruth Dassonneville, Nils B. Weidmann , and 3 more

kunkakom.bsky.social
Alexander Wuttke @kunkakom.bsky.social · 5d
🧵 PhD position (75%) in Political Behavior / Political Communication / CSS
📍 LMU Munich | ⏳ 3 years | 🗓 start March–May 2026

We’re hiring for DemocraGPT, a @bidt.bsky.social-funded project developing an AI-based training for difficult conversations in times of growing polarization

Reposted by Ingo Rohlfing

djnavarro.net
Danielle Navarro @djnavarro.net · 5d
A request for #rstats help.

Motivated by a real-world problem I'm facing, I wrote a package designed to help new users wean themselves off using rm(list=ls()), and nudge them in the direction of better practice.

I would sincerely appreciate feedback before I send it to CRAN
Some thoughts on checking the R session – Notes from a data witch
More precisely, some thoughts on an R package I might send to CRAN, and I’d appreciate comments and criticism
blog.djnavarro.net

ingorohlfing.bsky.social
Ingo Rohlfing @ingorohlfing.bsky.social · 6d
Mark transmission and conserved quantity have been devised with an eye on physics / natural science, so I generally find it hard to transfer this to the social sciences.
For mechanistic theories that are more popular in qual political science, I find it hard to see the criterion for causal inf

Reposted by Ingo Rohlfing

dingdingpeng.the100.ci
Julia M. Rohrer @dingdingpeng.the100.ci · 6d
Here's a question for the causal inference people: What is your take on causality without counterfactuals and/or causal inference without counterfactuals?
a cartoon of a man holding a box that says ' w ' on it
Alt: The Farnsworth Parabox
media.tenor.com

ingorohlfing.bsky.social
Ingo Rohlfing @ingorohlfing.bsky.social · 7d
I like colorhighlighting in equations, either of the brackets or element of an equation. It requires much more typesetting, in particular if one would want to do in a colorblind-friendly manner, but probably worth it.

Reposted by Brian A. Nosek, Seema Jayachandran, Ingo Rohlfing , and 3 more

kjhealy.co
Kieran Healy @kjhealy.co · 7d
Meanwhile, a Crossover Episode.
Bill Ackman Says He Has Funded Francesca Gino’s Legal Defense Since June 2024 | News | The Harvard Crimson
Billionaire hedge fund manager Bill A. Ackman ’88 said he has been funding the legal defense of Francesca Gino, a former Harvard Business School professor accused of research fraud, since June 2024, c...
www.thecrimson.com

ingorohlfing.bsky.social
Ingo Rohlfing @ingorohlfing.bsky.social · 12d
Übermorgen gefolgt von 20+ Predictions über was auch immer für 2026

Reposted by Ingo Rohlfing, Sebastian Karcher

kunkakom.bsky.social
Alexander Wuttke @kunkakom.bsky.social · 15d
The sale pitch for this AI Scientist "Kosmos" as presented in this Podcast just seems like a big HARKing exercise. Yes, just look at the data long enough and you'll find "something".

Has anybody made any experiences with AI scientists models? Recommendations?
pca.st/episode/58aa...
Where Is All the A.I.-Driven Scientific Progress?
pca.st

ingorohlfing.bsky.social
Ingo Rohlfing @ingorohlfing.bsky.social · 18d
What's the occasion this time?

ingorohlfing.bsky.social
Ingo Rohlfing @ingorohlfing.bsky.social · 19d
It is very short and not research, so one can hardly fool anyone, but I agree its misrepresentation should be avoided. Maybe the publisher messed it up, things can go wrong at many stages of the process.

ingorohlfing.bsky.social
Ingo Rohlfing @ingorohlfing.bsky.social · 21d
I see, I believed it was only about fake citations. This is then indeed much harder.

ingorohlfing.bsky.social
Ingo Rohlfing @ingorohlfing.bsky.social · 21d
It seems necessary now to validate citations. I assume there exists a tool for this or, if not, that one will be developed soon. One would not even need an "AI-powered" tool for this, just a tool for verified publication records, like OpenAlex maybe?

Reposted by Ingo Rohlfing

Andrew Gelman et al. @statmodeling.bsky.social · 21d
“I think there’s an argument to be made that much meta-scientific work is a kind of mirror image of the empirical work it critiques”
statmodeling.stat.columbia.edu/2025/12/21/i...
“I think there’s an argument to be made that much meta-scientific work is a kind of mirror image of the empirical work it critiques” | Statistical Modeling, Causal Inference, and Social Science
statmodeling.stat.columbia.edu

Reposted by Iain Davidson, Charles West, Lesley A. Hall , and 11 more

aryazandvakili.bsky.social
Arya Zandvakili @aryazandvakili.bsky.social · 22d
When viewing the fake article in Google scholar on my university network, there is a link to access the article via my uni's library. That link sends me to a library page that makes fake article appear real... Turns out library page is made programmatically from info on Google scholar 🤦

ingorohlfing.bsky.social
Ingo Rohlfing @ingorohlfing.bsky.social · 25d
Perhaps Google Scholar is irrelevant enough to Google to be worth shutting down.

ingorohlfing.bsky.social
Ingo Rohlfing @ingorohlfing.bsky.social · 25d
Of course, the overall problem is that citations and citation indices are taken to be important in the article and by many researchers. If we wouldn't care about citations, it would not matter that GS is screwing up metrics. 4/

ingorohlfing.bsky.social
Ingo Rohlfing @ingorohlfing.bsky.social · 25d
Some researchers may have noticed their inflated citation counts and decided not to correct them. If so, this would be shortsighted because a cursory look at the cited publications most likely shows that something is off, devaluing the whole citation record of this person. 3/

ingorohlfing.bsky.social
Ingo Rohlfing @ingorohlfing.bsky.social · 25d
With regard to Google Scholar, it reads like a "yes, but" argument. Google's careless assignment of publications to names is the root error. I guess Google could do much better, but, as the article states, Google does not care about at all about improving GS. 2/

ingorohlfing.bsky.social
Ingo Rohlfing @ingorohlfing.bsky.social · 25d
Google Scholar’s citation errors skew h-index leaderboards
www.timeshighereducation.com/news/google-...
"Thousands of mistakenly awarded citations left uncorrected highlight the perils of leaving profile curation to academics, say critics"
I don't quite agree with the focus taken in this article 1/

Reposted by Ingo Rohlfing, Paul Nightingale, Jan R. Boehnke

rmcelreath.bsky.social
Richard McElreath 🐈‍⬛ @rmcelreath.bsky.social · 25d
The Max Planck Society has begun an exploratory round table for open science. We are drafting some recommendations to leadership. Still a long way to go! But here are my notes on the most recent draft, just so you all know how I am trying to steer things.
Richard McElreath: It must not be overlooked that junior researchers DO NOT TRUST US. We, the directors, are a big part of the problem. We made this system, we remake it every year, and we benefit from it. What can we do to credibly signal our commitment to reform a corrupt research culture? My conversations with junior scientists in the society has taught me that directors are too often either indifferent or hostile to science reform. We cannot hope to convince our prize winning colleagues. Their egos are immune. But we can replace retirements with researchers who care more about integrity than their own prestige. This is important both for earning the trust of the junior researchers who really do the research in the MPG and for attracting excellent future directors and starting to earn the trust of the public. So I suggest two strong signals to our junior researchers (and the public): (1) we will reform recruitment and promotion at all levels to eliminate proxies like citation counts and journal brands in favor of reliability and sustainability; (2) we will make open science skills a core part of scientific training, through the graduate schools at a minimum, as conditions for the central funding. The most ambitious thing we could do, as hinted at in item 5 above, is to meaningfully invest in metascientific research. As the largest basic research organization in the world, the MPG is uniquely suited to studying research and its products from a broad perspective that includes the humanities, the sciences, and policy. Governments are already involved in science reform. Someone should study it in an organized and sustained way.