Ingo Rohlfing

The Coming Apocalypse for Scientific Publishing Price was right

The volume of AI-enabled decent scientific work will overwhelm scientific journals and reviewers. Good post about this except it ends on a strange note, that Wiley and Elsevier AI tools might save us, which is both unlikely and would give even more power to them.
open.substack.com/pub/thebsdet...

I guess Stata is working on an AI integration bc it knows it will be toast otherwise in the medium run. At a reasonable pricing level, this may help in securing current subscribers. I am uncertain this will help in the long run bc it may not be attractive enough as an entry point to data analysis.

I'm sceptical of most "AI will kill [insert job/field/method]" takes, but I'm increasingly of the view that AI will kill Stata. What's the point in paying for it when a Claude Code Max subscription costs about the same and does the same things and more in R/Python, exponentially faster and better?

README Checklist by the Data Editors of Review of Financial Studies
review-of-financial-studies.github.io/readme.html An extensive checklist that is very useful. README files are likely something that is left for LLMs in the future, but it could be based on this template then. #OpenScience

The way I think about this is that the distribution of effects is approximately sparse (most effects are very weak but nonzero). Journals/researchers are interested in effects that are surprising given that prior distribution.

Yes but a 2c from this political scientist:

1) in polisci, which is more open to qual methods/soft data than econ, the claude code shock may mean that qual data & original measurements will increase value

2) that "hopefully" is doing *a lot* of work but again women tend to select in qual meth so 🤞

This, probably in combination with some R+R demands having marginal benefit for improving a manuscript.

Every academic in their 40s goes through this career/life stage where they decide that the journals are broken and stupid. It's mostly because they are bored of working on R+Rs given that the marginal benefit for their own career of another publication is close to zero.

The case for sharing clinical trial data The story behind the first statin and how its development was almost derailed, and the implications of sharing clinical trial data.

New short blogpost!

There are probably many benefits of sharing clinical trial data, including:

Verifying results, better meta-analysis, understanding inconsistent results, further exploration, better clinical decision-making, learning how to run trials better, and reducing redundancy.

Neuer Bereich auf der meta-IFiF-Website Sie möchten wissen, wie Forschungsprojekte dazu beitragen, innovative Frauen sichtbarer zu machen? Auf unserer Website finden Sie jetzt die

💡Wie tragen #Forschungsprojekte dazu bei, die #Sichtbarkeit innovativer Frauen zu erhöhen? Forschungsergebnisse, Maßnahmen und Formate finden Sie auf unserer Website! @bukof.bsky.social @frauenrat.bsky.social @infect-net.bsky.social @aktarcha.bsky.social @ruhr-uni-bochum.de @unidue.bsky.social

Dann habe ich eine Ahnung, was das Bundesland angeht. Es sei denn, alle haben mittlerweile Scientologyfragebögen. So oder so, mein Glückwunsch und gut, dass eine deutsche Uni dich gewinnen konnte.

Wo geht es hin?

I forgot about this or missed it when reading the text. Technically, this seems correct, but besides everything else, the equal weighting of models is not plausible. Did anyone ever do this? I better not check.

This is a very useful, non-technical discussion of the multiverse analysis. Personally, I like the "Don't take it too seriously" attitude, though it is probably unsatisfying for someone who thinks about using it and wants a more definitive answers (sometimes, this is not what one gets)

What’s a multiverse good for anyway? Julia M. Rohrer, Jessica Hullman, and Andrew Gelman Multiverse analysis has become a fairly popular approach, as indicated by the present special issue on the matter. Here, we take one step back and ask why one would conduct a multiverse analysis in the first place. We discuss various ways in which a multiverse may be employed – as a tool for reflection and critique, as a persuasive tool, as a serious inferential tool – as well as potential problems that arise depending on the specific purpose. For example, it fails as a persuasive tool when researchers disagree about which variations should be included in the analysis, and it fails as a serious inferential tool when the included analyses do not target a coherent estimand. Then, we take yet another step back and ask what the multiverse discourse has been good for and whether any broader lessons can be drawn. Ultimately, we conclude that the multiverse does remain a valuable tool; however, we urge against taking it too seriously.

New preprint! So, what's a multiverse analysis good for anyway?>

With @jessicahullman.bsky.social and @statmodeling.bsky.social

juliarohrer.com/wp-content/u...

A handdrawn of an imaginated open science land. It has as parts documentation, planning, dissemination, sea of myths and peninsula of dreams

Welcome to #OpenScience Land
expedition-open-science.org This is a lightweight, but very useful and accessible intro to key elements of Open Science (online and as a PDF). Seems particularly useful for introducing the topic to undergraduates @zbw-leibniz.bsky.social

Screen shot of a youtube video titled "AI.FILL Function Explained: 10X Productivity in Excel with AI" with the caption "Let ChatGPT fill your missing data"

Don't you f**king dare.

Here’s What the Latest Epstein Files Say About His Ties to Higher Ed New documents released by the Department of Justice on Friday reinforce that long after his criminal convictions, many prominent professors continued to communicate with him.

Here’s What the Latest Epstein Files Say About His Ties to Higher Ed: Collectively, the files underscore how deeply Epstein remained embedded in academic and intellectual circles even after his criminal history became public. www.chronicle.com/article/here...

From X: Renaud Foucart @RenaudFoucart Few people now this but the Epstein library can be used to bypass academic journal paywalls. You search for a paper and if someone sent it to Epstein the pdf is there.

New sci-hub just dropped.

I wrote a blog for the Meta-Research Center expressing my infinite frustration about not getting data. What else is new, you might think? Well, I added an extra layer of annoyance directed at the journals who do NOTHING to enforce promised data sharing.

metaresearch.nl/blog/2026/2/...

🧵 New version of our paper (@bcegerod.bsky.social) is finally online: "How Many is Enough? Sample Size in Staggered Difference-in-Differences Designs"
We show that even well-identified DiD studies are often underpowered; sample sizes needed are surprisingly large
Paper: osf.io/preprints/os... 1/6

Nine More Higher Ed Names in the Epstein Files
www.insidehighered.com/news/faculty...

It is good more attention is paid to power.
In what way do we get to our senses? That more studies estimate power, or acknowledge that power is likely to be low?

Good point, this is plausible to me.

I think this is unlikely to happen, but who knows. Let's see how this plays out at Small Business Economics and how the first registered report will look like. 2/

Sorry, I was fully focused on the prereg part, not the reports part. Right, results-blind review would likely still work. Theoretically, if you were submitting your code with the registered report and the original data were sitting in some repo, a reviewer could quickly do the analysis. 1/

Not to downplay the value of the format, which is great, but these kind of studies do not open much opportunity for replications because new data would be hard to collect or it may not be possible when the original study already worked with all population-level data 3/

the data little insightful. It does not mean the data do not exist at the time of prereg, but there should be some credibility of the inaccessibility part.
Maybe the editors have a different view because, according to the online-first articles, most seem to work with survey, firm or country data 2/

I don't know, we should ask the editors what they mean to be sure. "and/or in a different context" does not read like new data to me when they refer to new data before that.
I am fine with anyone having a different read of and view on this. Personally, I find prereg with ex ante accessibility of 1/

The FORRT Replication Database has received a massive overhaul (FReD 2.0): We double-coded and validated all data from scratch and extended it in the course of a one-year-partnership with the @cos.io. We just switched to a faster interface thanks to @lukaswallrich.bsky.social’s wizardry.