Jesper Wulff | Lightnews

Jesper N. Wulff

@jnwulff.bsky.social

670 followers 950 following 40 posts

Professor @AarhusUni doing research on organizational research methods and teaching deep neural networks in our Msc. BI program. https://sites.google.com/view/jesperwulff/bio

Videos

Business 66%

Economics 34%

Posts Replies Media Videos

Reposted by John A. Finn, Jesper Wulff

Darren Dahly @statsepi.bsky.social · 14h

🎯

statsepi.substack.com/p/the-review...

Reposted by Jesper Wulff

Richard @rwpickard.bsky.social · 10d

Some comments on PubPeer: pubpeer.com/publications...

PubPeer - Bridging the gap: explainable ai for autism diagnosis and pa...

There are comments on PubPeer for publication: Bridging the gap: explainable ai for autism diagnosis and parental support with TabPFNMix and SHAP (2025)

pubpeer.com

Erik Angner @erikangner.com · 10d

"Runctitiononal features"? "Medical fymblal"? "1 Tol Line storee"? This gets worse the longer you look at it. But it's got to be good, because it was published in Nature Scientific Reports last week: www.nature.com/articles/s41... h/t @asa.tsbalans.se

Infographic with AI slop published in Nature Scientific Reports

Reposted by Jesper Wulff

Andrew Heiss @andrew.heiss.phd · 16d

hahahaha just got an email from someone who was using Claude to generate a boilerplate #QuartoPub document and the LLM *used my name* as the author. The computers are literally trying to be me now 😂🤣🙃🫠

A Quarto document in RStudio with the author field set to "Andrew Heiss"

Jesper N. Wulff @jnwulff.bsky.social · 17d

Which tools are you using for making them?

Reposted by Felicity Callard, Lindsay M. Tedds, Dana R. Fisher , and 4 more Felicity Callard, Lindsay M. Tedds, Dana R. Fisher, Lisa Diedrich, Marcus Credé, Melinda Baldwin, Jesper Wulff

ElieNYC @elienyc.bsky.social · 18d

I know that at this point it's a subplot in the Epstein files drama, but I feel compelled to point out, once again, that Larry Summers HAS NO BUSINESS teaching students at ANY university ever again!

My latest cries into the abyss, in @thenation.com

www.thenation.com/article/soci...

Why Is Larry Summers Still Employed?

The revelations about the economist’s attempts to pressure a women into a “relationship”—with guidance from Jeffrey Epstein—should finally disqualify him from teaching students.

www.thenation.com

Jesper N. Wulff @jnwulff.bsky.social · 20d

I've used your book several times for a graduate course on Bayes stats for business and data science students with great success. If you divide into beginner and adv. I imagine the first half would fit well for a bachelor level course.

Reposted by Cas Mudde, Anna O. Law, Kim L. Scheppele , and 48 more Cas Mudde, Anna O. Law, Kim L. Scheppele, Heidi Altman, Richard S.J. Tol, Norbert Schwarz, Nancy Kanwisher, John F. McCarthy, Stefan Reis, Brendan Nyhan, Linda J. Skitka, Gavin A. Schmidt, Jesse H. Kroll, John R. Hutchinson, Bryan D. Jones, Glenn Lyons, Rosemary A. Joyce, Jonathan M. Gilligan, Melissa R. Michelson, Philip Nel, Anders Nilsson, Melanie C. Green, W. Andy Knight, Julia Lynch, Roopika Risam, Gerald Friedman, Alison Johnson, Mary L. Dudziak, Rebecca M. Bratspies, Michael D. McDonald, William Myers, Dana R. Fisher, Nikolay Marinov, Jason Lyall, Daryl Adair, Erin O’Donnell, Thomas Masterson, Sharon S. Dawes, Nelson Flores, Alessandro Rigolon, Nicole Guenther Discenza, Linda L. Berger, Annette Yoshiko Reed, Jean Kazez, Dan Immergluck, Sylvia Perry, Timothy D. McBride, Dunlap, Deborah M. Kolb, Adam M. Kleinbaum, Jesper Wulff

Aaron Parnas @aaronparnas.bsky.social · 20d

NEW: Epstein survivors release the most powerful PSA I have ever seen.

Make this go viral so every member of the House of Representatives sees it.

Reposted by Dorothy Bishop, Ian Hussey, Jesper Wulff

Retraction Watch @retractionwatch.com · 21d

A paper critiquing post-publication peer review has numerous made-up references, including a @nature.com article falsely attributed to our Ivan Oransky.
link.springer.com/article/10.1...

PubPeer - An expert criticism on post-publication peer review platform...

There are comments on PubPeer for publication: An expert criticism on post-publication peer review platforms: the case of pubpeer (2025)

pubpeer.com

Reposted by Johannes Breuer, Jesper Wulff

Cursor @cursortue.bsky.social · 24d

TU/e has gained a new research centre: META/e. Daniël Lakens and Krist Vaesen were among the founders of this knowledge hub for metascience—research aimed at improving the practice of science itself. “We want to be a home for every researcher who occasionally wonders: what are we even doing?”

Knowledge centre META/e: home for those improving science

www.cursor.tue.nl

Jesper N. Wulff @jnwulff.bsky.social · Nov 1

Yes!!

Anne Scheel @annemscheel.bsky.social · Oct 31

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/ >

Reposted by Gordon Pennycook, Alexander Wuttke, Ingo Rohlfing , and 2 more Gordon Pennycook, Alexander Wuttke, Ingo Rohlfing, Dean Eckles, Jesper Wulff

Anne Scheel @annemscheel.bsky.social · Oct 31

Reposted by Jesper Wulff

Daniel Lakens @lakens.bsky.social · Sep 28

New blog post on Gelman's recent claim that Type S and M errors are intended as a 'rhetorical tool', and if I was wrong to believe they were recommended more routinely in our recent preprint criticizing the idea of Type S and M errors. daniellakens.blogspot.com/2025/09/type...

Type S and M errors as a “rhetorical tool”

We recently posted a preprint criticizing the idea of Type S and M errors ( https://osf.io/2phzb_v1 ). From our abstract: “While these conce...

daniellakens.blogspot.com

Jesper N. Wulff @jnwulff.bsky.social · Sep 25

What corresponds to the Z-test in this analogy? If the P-curve is the W-test then what is the Z-test?

Reposted by Jesper Wulff

Richard Sever @richardsever.bsky.social · Sep 23

More examples of faked institutional email addresses from @deevybee.bsky.social here deevybee.blogspot.com/2022/10/what...

Jesper N. Wulff @jnwulff.bsky.social · Sep 16

9 Equivalence Testing and Interval Hypotheses – Improving Your Statistical Inferences share.google/tZRu9HekIBdY...

9 Equivalence Testing and Interval Hypotheses – Improving Your Statistical Inferences

This open educational resource contains information to improve statistical inferences, design better experiments, and report scientific research more transparently.

share.google

Jesper N. Wulff @jnwulff.bsky.social · Sep 16

Absolutely! I'm planning on getting met into the stats curriculum in our undergrad business adm program. My favorite resource is Lakens' online book.

Jesper N. Wulff @jnwulff.bsky.social · Sep 16

If it makes sense to test a hypothesis, do minimum effect testing and/or set alpha as a function of sample size.

Reposted by Alexander Wuttke, Christian Breunig, Graham Webster , and 6 more Alexander Wuttke, Christian Breunig, Graham Webster, Patrick Präg, Johannes Breuer, Larry W. Hunter, Aleksandra Urman, Samuel Coavoux, Jesper Wulff

Joachim Baumann @joachimbaumann.bsky.social · Sep 12

🚨 New paper alert 🚨 Using LLMs as data annotators, you can produce any scientific result you want. We call this **LLM Hacking**.

Paper: arxiv.org/pdf/2509.08825

$We present our new preprint titled "Large Language Model Hacking: Quantifying the Hidden Risks of Using LLMs for Text Annotation". We quantify LLM hacking risk through systematic replication of 37 diverse computational social science annotation tasks. For these tasks, we use a combined set of 2,361 realistic hypotheses that researchers might test using these annotations. Then, we collect 13 million LLM annotations across plausible LLM configurations. These annotations feed into 1.4 million regressions testing the hypotheses. For a hypothesis with no true effect (ground truth $p > 0.05$), different LLM configurations yield conflicting conclusions. Checkmarks indicate correct statistical conclusions matching ground truth; crosses indicate LLM hacking -- incorrect conclusions due to annotation errors. Across all experiments, LLM hacking occurs in 31-50\% of cases even with highly capable models. Since minor configuration changes can flip scientific conclusions, from correct to incorrect, LLM hacking can be exploited to present anything as statistically significant.$

Reposted by Jesper Wulff

Marieke van Vugt @mvugt.bsky.social · Sep 9

"OpenAI is making “small steps that are good, but I don’t think we’re anywhere near where we need to be”, says Mark Steyvers, a cognitive science and AI researcher at UC Irvine. “It’s not frequent enough that GPT says ‘I don’t know’.”" www.nature.com/articles/d41...

Can researchers stop AI making up citations?

OpenAI’s GPT-5 hallucinates less than previous models do, but cutting hallucination completely might prove impossible.

www.nature.com

Reposted by Juan Moreno‐Cruz, Jesper Wulff

Paul Hünermund @p-hunermund.com · Aug 30

➡️ Deadline approaching—only one month left to send in your papers and presentation proposals for #CDSM2025!

🚨 𝗖𝗮𝗹𝗹 𝗳𝗼𝗿 𝗣𝗮𝗽𝗲𝗿𝘀: 𝗖𝗮𝘂𝘀𝗮𝗹 𝗗𝗮𝘁𝗮 𝗦𝗰𝗶𝗲𝗻𝗰𝗲 𝗠𝗲𝗲𝘁𝗶𝗻𝗴 𝟮𝟬𝟮𝟱 🚨
📅 𝗡𝗼𝘃 𝟭𝟮–𝟭𝟯, 𝟮𝟬𝟮𝟱 (𝗩𝗶𝗿𝘁𝘂𝗮𝗹)
📥 Submission Deadline: 𝗦𝗲𝗽𝘁 𝟯𝟬, 𝟮𝟬𝟮𝟱

Julia M. Rohrer @dingdingpeng.the100.ci · Aug 25

Ever stared at a table of regression coefficients & wondered what you're doing with your life?

Very excited to share this gentle introduction to another way of making sense of statistical models (w @vincentab.bsky.social)
Preprint: doi.org/10.31234/osf...
Website: j-rohrer.github.io/marginal-psy...

Models as Prediction Machines: How to Convert Confusing Coefficients into Clear Quantities

Abstract
Psychological researchers usually make sense of regression models by interpreting coefficient estimates directly. This works well enough for simple linear models, but is more challenging for more complex models with, for example, categorical variables, interactions, non-linearities, and hierarchical structures. Here, we introduce an alternative approach to making sense of statistical models. The central idea is to abstract away from the mechanics of estimation, and to treat models as “counterfactual prediction machines,” which are subsequently queried to estimate quantities and conduct tests that matter substantively. This workflow is model-agnostic; it can be applied in a consistent fashion to draw causal or descriptive inference from a wide range of models. We illustrate how to implement this workflow with the marginaleffects package, which supports over 100 different classes of models in R and Python, and present two worked examples. These examples show how the workflow can be applied across designs (e.g., observational study, randomized experiment) to answer different research questions (e.g., associations, causal effects, effect heterogeneity) while facing various challenges (e.g., controlling for confounders in a flexible manner, modelling ordinal outcomes, and interpreting non-linear models).

Figure illustrating model predictions. On the X-axis the predictor, annual gross income in Euro. On the Y-axis the outcome, predicted life satisfaction. A solid line marks the curve of predictions on which individual data points are marked as model-implied outcomes at incomes of interest. Comparing two such predictions gives us a comparison. We can also fit a tangent to the line of predictions, which illustrates the slope at any given point of the curve.

A figure illustrating various ways to include age as a predictor in a model. On the x-axis age (predictor), on the y-axis the outcome (model-implied importance of friends, including confidence intervals).

Illustrated are
1. age as a categorical predictor, resultings in the predictions bouncing around a lot with wide confidence intervals
2. age as a linear predictor, which forces a straight line through the data points that has a very tight confidence band and
3. age splines, which lies somewhere in between as it smoothly follows the data but has more uncertainty than the straight line.

Reposted by Jesper Wulff

Theiss Bendixen @theissbendixen.bsky.social · Aug 25

"Being Bayesian in a Frequentist World"

New post on "Bayesian dynamic borrowing" in R 📚

Link 👇

Reposted by Dorothy Bishop, Brady T. West, Jürgen Maier , and 8 more Dorothy Bishop, Brady T. West, Jürgen Maier, Philip N. Cohen, Alexander Wuttke, Pierre Bataille, Martin Bækgaard, Alessandro Nai, Tom Chevalier, Juan Fernández, Jesper Wulff

Daniel Lakens @lakens.bsky.social · Aug 25

If you are preparing your bachelor statistics course and would like to add optional material for students to better understand statistics on a conceptual level (see topics in the screenshot) my free textbook provides a state of the art overview. lakens.github.io/statistical_...

Reposted by Jack Stilgoe, Jesper Wulff

Dr. Casey Fiesler @cfiesler.bsky.social · Aug 23

My video about how LLMs are not search engines has led to many, MANY comments telling me that I should be using Perplexity. Some insisting that Perplexity does not hallucinate.

Out of a list of 26 papers it just provided me (in "Research" mode) 4 were real. FOUR. 85% hallucination rate.

Reposted by James M. Bullock, Robert Metcalfe, Barrett , and 1 more James M. Bullock, Robert Metcalfe, Barrett, Jesper Wulff

Saloni @scientificdiscovery.dev · Aug 17

TIL the original paper describing CRISPR, by Francisco Mojica, was rejected by 4 journals and took 2 years to be published

Reposted by Matthew J. Kuehnert, Steve Peers, Markus Jäntti , and 5 more Matthew J. Kuehnert, Steve Peers, Markus Jäntti, Jussi T. Eronen, Larry W. Hunter, Greg Linden, Elisa Freschi, Jesper Wulff

Carl T. Bergstrom @carlbergstrom.com · Aug 16

Just in case there was any doubt, ChatGPT 5.0 still makes up completely random citations that don't exist and should not be used for literature search.

1. David Ackerly (UC Berkeley)

While his most-cited work is on leaf size and SLA, he also wrote explicitly about plasticity in leaf traits, including shape, in the context of ecological strategies.

Example: Ackerly (1997), “Allocation, leaf display, and growth in fluctuating light environments: A comparative study of deciduous and evergreen species” (Oecologia). This emphasizes how plasticity in leaf traits mediates adaptation to light.

Reposted by Richard S.J. Tol, Dorothy Bishop, Jesper Wulff

Carlisle Rainey 👨‍💻📊📚 @carlislerainey.bsky.social · Aug 12

‼️Cool new paper‼️

Finds that journal data policies in psychology boost sharing statements to ~100%, but only about half of datasets are complete, understandable, reusable.

Open: open.lnu.se/index.php/me...