I wrote a blog post on the science behind The Atlantic's "no alcohol for fathers-to-be" piece. quentinandre.net/posts/drunk-...

ALL the papers from Michael Golding's lab cited in this piece (the scientist claiming a causal impact of paternal alcohol consumption on fetal outcomes) suffer from pseudoreplication issues. Treatment administered on sires, analysis conducted on pups without random effects.

Quentin André@quentinandre.bsky.social · 3w ago

Any statistican who has seen this before (insanely small p-values with small N) knows the most likely culprit: "Pseudoreplication", when non-independent observations are analyzed as if they were independent. Claude Opus 4.8 provides an exellent summary of the issue. 5/N

I wish journalists reported more carefully on science. I really do. A short thread. The study cited at in the intro of this article is a mice study. Researchers randomize male to have access to a low/med/high amount of ethanol... 1/N www.theatlantic.com/family/2026/...

HBS' latest filing in the Gino lawsuit contains a few new details: 1. A committee of 26 professors, admins, and fellows reviewed the allegations, and *unanimously concluded* that there was *clear and convincing evidence* of research misconduct.

New blog post: Make Your Papers Legible to Machines (They’re Already Reading) quentinandre.net/posts/legibl...

Hallucinate cites? Claims that contradict the content of the paper? Conspiratorial tone implying her program of research was silenced by shadow forces? Loose understanding of statistics? How can a rigorous scientist show such lapses in judgment? Unless...

Daniel Lakens@lakens.bsky.social · 2mo ago

New blog post: Evaluating Dr. Cuddy’s Claim that the Debunking of Power Posing is a Myth. daniellakens.blogspot.com/2026/05/eval... On an AI generated description of a non-existent study, incorrectly citing findings from studies, and the importance of scientific criticism.

"Reviewers... are going to become less tolerant of these “obvious” big mistakes now that they can be identified by a variety of cheap tools [GenAI review apps] prior to publication... The least we can do is ask them to review the best possible version..." via @quentinandre.bsky.social

Just finished migrating my academic website to Quarto, with Claude Code's invaluable help. To celebrate, a new blog post: "What I Keep Flagging in My Reviews": quentinandre.net/posts/what-i...

My husband asked me to help him identify this material — is this floss?

Yep yep yep quentinandre.net/post/making-...

Increasing the Informativeness of Power Analysis | Quentin André

If power analysis cannot be based on the expected effect size, what should it be based on?

quentinandre.net

Gordon Pennycook@gordpennycook.bsky.social · 5mo ago

My own take on power analyses: I'm good with "we had xx power to detect effects as big as xx" but find "we made a pseudo-random guess about an effect size & determined that we need a sample of N=[some highly specific number]" to be too close to cosplay for me.

excellent piece, and should be required reading for anyone skeptical of the technical capabilities and policy implications of AI. there are certainly exceptions, but by and large, the political left is currently treating what should be a five-alarm fire like a distasteful spectator sport.

The left is missing out on AI

As a movement, it has largely refused to engage seriously with AI, ceding debate about a threat and opportunity to the right

transformernews.ai

Very important paper, both empirically (for our understanding of human behavior) and methodologicaly (for our future inquiries into human behavior).

sjdm-tweets@sjdm-tweets.bsky.social · 7mo ago

Today's SJDM Featured Paper is: Dietvorst, B. J. (in press). Understanding people's preferences for predictions: People prioritize being right over minimizing how wrong they are in expectation. Management Science. doi.org/10.1287/mnsc...

After a popular psychological manipulation turns out to be non-replicable (e.g., "in a seemingly unrelated task" behavioral priming interventions), it is always fun to go back and find the papers who reported "p < 10e-8" effects. No, wait, it's not fun actually.

This hasn't received much attention, but it looks like scammers also hacked into Francesca Gino's MTurk account, and asked MTurkers to buy her book Rebel Talent to boost the first-week sales of the book. Poor lady cannot catch a break. (links in comments)

If you want to submit your research to HotFresh Research News or find a boilerplate letter to refuse reviewing for closed journals, visit this link learnmoore.org/hotfresh.html

For Sunday at the SJDM conference, please note the following changes to the program!

Repost this to let people know you are at SJDM 2025 in Denver! Tag @sjdm-tweets.bsky.social if you would like us to repost stuff that you post! #SJDM2025

If you're attending @sjdm-tweets.bsky.social or @psychonomicsociety.bsky.social this week, do not print your poster on site at the convention center -- it's $100 more! There's a FedEx a short walking distance away. Please tell your students!!

Halloween is the best holiday. Change my mind.

When it's Halloween, but your 2.5yo daughter insists that "we should bring the skeleton inside" and "make it cozy with a blankie and a pillow".

take this quiz then tell me you can win over low-info "moderates" on policy it's just vibes all the way down

Quantian@quantian.bsky.social · 9mo ago

Take this quiz to die instantly www.americansurveycenter.org/quiz/

An LLM-produced essay is tangible proof that a student doesn’t care, and yet responding to it properly requires hour upon hour of careful work. It’s asymmetrical and overwhelming.

Cheating with an LLM is the easiest thing in the world for a student to do, but it creates a massive, laborious headache for a prof, if you intend to take it seriously. There’s meetings, emails, discussions, moral dilemmas. It’s just incredibly burdensome, on top of everything else right now.

Corinne Gressang@corinnegressang.bsky.social · 9mo ago

I had 9 meetings about students using Chat GPT/LLMs on their papers today. If you want to know why professors burn out, ask anyone trying to teach critical thinking and writing skills to Freshmen....

Wait until you learn about common ways of doing segmentation analysis in marketing. "Yeah, we ran a K-means algorithm, gave each cluster a cute name and a persona, and now we're making every decision based on whether Pumpkin-Spice Peggy or Truck-Nut Terry will like it".

Julia M. Rohrer@dingdingpeng.the100.ci · 9mo ago

It’s astonishing how many researchers seem to believe that a cluster analysis is such a sensible analysis that it needn’t even be justified through a coherent research question. Just cluster analysis go brrrrr

Cool and normal

If, as a reviewer, you see an unusual statistical test being reported in a manuscript, it never hurts to double-check whether the test does what the authors claim. Who knows, it might help a journal not publish inaccurate results.

I have many thoughts about Charlie Kirk—and perhaps even more about the white elites, including some on the left, who insist we can’t hold multiple realities at once. We can. And we must. A brief 🧵

I'll admit, I was skeptical when they said Gemini was just like a bunch of PhDs. But I gotta admit they nailed it.