Finally, with these games we can settle who is the best statistician on bsky.

The gloomy headlines about the future of American higher ed been seemingly relentless. But the discourse is missing some basic(and surprising) facts about what’s actually happening right now. Here are 10....

5) The college-wage premium remains near historic highs. College-educated workers, on average, are paid substantially more than non-college workers. Rigorous studies suggest that a good chunk of this premium is causal.

Thank you @natureportfolio.bsky.social for making my review of the Anxious Generation open access for parents, policy-makers, and the public. The story told in this book runs counter science and is leading to poor policy decisions that will ultimately fail our kids. www.nature.com/articles/d41...

A review of 18 studies found no consistently reproducible subtypes of schizophrenia, suggesting that differences in brain structure across patients may reflect a spectrum rather than discrete biological categories.

Two thoughtful essays about the impact of LLMs on graduate education: ergosphere.blog/posts/the-ma... economics.mit.edu/sites/defaul... From personal experience I think the self-control problem mentioned in the first essay is very real.

Are women more attracted to men with resources? It depends. Romantic preferences for people with economic resources are stronger for the sex that is poorer and individuals who are poorer. This suggests that economic preferences are cultural, rather than evolutionary. www.pnas.org/doi/10.1073/...

Ian Hussey (@ianhussey.mmmdata.io) contacted me about the recurring problem of unusually large SMD values appearing in published meta-analyses. Very large SMDs can result from using SEs in place of SDs in their calculation, which is a mistake I have also seen in practice. 1/4

Wimsatt: Perhaps, just perhaps, the best explanation of a phenomenon at a given level is to be found at the same level. Kendler: Noone would seek to explain hypertension at the level of quarks. A few of my favourite papers on this topic of absurd biological reductionism: 🧵

This...the fetishizing of unreplicable neuroscience in order to legitimize our work is self-defeating. We don't need to know that depression is in the brain (as opposed to what???) to know it is problematic. How much money have we wasted proving something like depression is "real"?

It seems clear there are important connections between personality research and motivation with implications for education research. I'm super excited this paper, which explores those connections, is in our forthcoming topical collection in Educational Psychology Review! #PsychSciSky #EduSky

Selecting an effect size for power analysis is hard. Many researchers fall back on Cohen's thresholds, but they have no empirical basis and vary wildly by field. Our new paper offers a better option: field-specific effect size distributions built from meta-analytic data doi.org/10.3758/s134...

I want to defend punching down in academia. Scratch that. I want to defend punching, full stop. Up, down, sideways. The norm against critiquing junior scholars publicly comes from a good place but breaks something fundamental about how science works. New essay. open.substack.com/pub/michaeli...

Reminder: when authors observe Cohen's d = 4, no they didn't. Article now retracted: www.nature.com/articles/s41... Critique: osf.io/preprints/ps... Blog on plausibility of effect sizes: trustworthy.scientific.claims/posts/if-res...

"Thanks to the support of visionary venture capitalists working tirelessly to usher in an age of equality and prosperity, Cyberdyne is building Skynet, a neural network on the brink of achieving something tech billionaires could hitherto only dream of: self-awareness."

New paper— everyone is collecting intensive longitudinal data but recent review studies report that less than half of studies consider measurement/psychometrics. The paper covers a few foundational psychometric methods for ILD and provides a shiny app to apply them link.springer.com/article/10.3...

🚨NEW PREPRINT🚨 together with Jürgen Huber & Michael Kirchler: “Massaging Significance in the Age of Open Science: A Satirical Tutorial,” which is a public service for anyone unwilling to let inconvenient data get in the way of a compelling narrative. 😉 Link to preprint: osf.io/preprints/ps...

Good news everyone 🥳 Our (w @vincentab.bsky.social) primer on models as prediction machines (with the marginaleffects package) is finally officially published!> journals.sagepub.com/doi/10.1177/...

"With a free Skynet Edu account, students can gain the career-readiness needed to navigate an exciting future in which they will be hunted by a remorseless, nuclear-armed superintelligence seeking to annihilate the human race—which will later be revealed to be Skynet itself."

Reminder: If researchers find Cohen's d = 6, no they didn't. trustworthy.scientific.claims/posts/if-res...

The irreproducibility tango. It is a timeless story of repeatedly asking a dance partner to dance at a dance only to have them report that they don't dance, ever.

How every layer of science's "self-correcting machinery" failed when Iva Veseli and I simply wanted to reproduce the findings of a high-profile study on gut microbiome and autism: merenlab.org/2026/04/15/u...

God bless you @colsonwhitehead.com "Do you realize how much water and power it’d take to replicate the average writer’s narcissism, self-loathing and despair? It’d drain the Indian Ocean. You could light up Times Square for a year. We can’t afford it."

The UK’s proposed study of social media reduction in kids doubles down on a failed experimental protocol & is likely to produce misleading results. It’s easy to tear apart a study post-hoc so I’m putting my marker down before the study begins: This is a bad study. open.substack.com/pub/grimoire...

As part of my efforts to combat the COVID Amnesia Project, let's accurately remember what 3 influential laptop class doctors from Stanford said 6 years ago as COVID overflowed hospitals and morgues. They won't remind you. I will. My latest.

📎New Research in European Journal of Personality "How unusual are you?" Read the full article: doi.org/10.1177/0890... @aebackunims.bsky.social #PersonalityPsychology #EJP #EAPP

Blothar The Berserker Of GWAR Explains How Independent Journalism Is The Only Force As Powerful As GWAR. Subscribe to The Onion at membership.theonion.com.

To teach in the time of ChatGPT is to know pain arstechnica.com/science/2026...

Has transparency improved in clinical psychology? New cross sectional study from us (Bianca Kotoulas, Justine Blackwell & me). Adoption of transparent research practices has increased between 2012, 2018, & 2024, but aside from coi and funding disclosures, they remain uncommon osf.io/preprints/ps...

There is no McTry.

The ERROR project recruits independent experts to recheck social sciences papers’ data, statistics, methodology, code; now the project plans to publish the reviews in a new peer-reviewed journal. science.org/content/arti... @dalmeet.bsky.social @science.org #reproducibility

An exasperated Jason Collins bangs the drum he’s been beating for 10 years over a pure zombie study. The original research suggesting a little disfluency in communication stimulates more analytical reasoning is a spectacular replication failure: buff.ly/VxIUvYr

Direction of effect and success of publcation: a randomized study has really been done already! Thanks to @floriannaudet.bsky.social for pointing it out jamanetwork.com/journals/jam...

I was supposed to finish this March 31 and then the #Claude Code leak happened, handing me the perfect opening example Some of it has been in the works for longer: it's also a version of (part of) my #DHd2025 keynote titled "What makes LLMs so irresistible?" Read it here: doi.org/10.5281/zeno...

The governing body for 14 Dutch universities (UNL) has published a "Vision on Publication Culture" that is so inspiring and forward thinking. Worth a read for those trying to changes publishing and research assessment practices. Take a read: www.universiteitenvannederland.nl/files/public...

A new paper from the HiTOP Revisions Workgroup (and yours truly) on the conceptual and philosophical underpinnings of the framework. Recommended reading for anyone interested in questions of classification and psychopathology! Here’s the journal article: muse.jhu.edu/pub/1/articl...

What makes behavioral interventions work beyond the psychological theory they implement? Their format, level of engagement, delivery modality? In a new paper analyzing 274 interventions from 15 megastudies (4.1M+ participants), we tested 19 features: www.sciencedirect.com/science/arti... 1/2

The discussion yesterday led me to fix the links to this piece. If thinking about Cofnas has you thinking about so-called racial differences in behavior, you might be interested. The same argument in spelled out at greater length in Chapter 9 of my book. @ptrbck.bsky.social

New paper, out this week in PLOS One, suggests that most close relationship self-report measures are primarily capturing relationship quality 🧵 journals.plos.org/plosone/arti...

@#$@@# self-reflection. We've been self-reflecting since 2010 in psychology to no avail. Just directly replicate the damn study.

Oh, and another thing. Since 50% of our work is functionally a "hallucination" because we can't be bothered to directly replicate anything we do, maybe we should stop getting the vapors about Claude hallucinating a few references. Nothing more ironic than fake references in a paper of fake findings.

Since, once again, we find only 50% of our work is replicable, I think we now have a solution to the problem finding reviewers for our journals. Journal review should be a coin flip. That would take a lot of pressure off the system...

The Ctrl-Z Award: Recognizing the courage to correct or retract published work retractionwatch.com/ctrl-z-award/

Download our free and open source Zotero Replication Checker plug in at forrt.org/flora_zotero. Check entire libraries or single reports, add replications and original studies, have them linked and labelled, and get regular updates - all with privacy-preserving matching.

@briannosek.bsky.social I'm disappointed you didn't use this opportunity for a good April Fools joke, as in "everything replicates!!!". Arina K. Bones would have done that. Just saying.

New preprint out today (osf.io/preprints/ps...). We tested whether AI agents are actually infiltrating online surveys. Spoiler alert: they aren't Thread 🧵 [1/9]

Apparently we just need to replicate the damn study after all.

🧵1/ Our first meta-science paper (with 350+ coauthors) is published today in Nature. It presents one of the largest-ever reproducibility projects in economics & political science. Here’s what we found 👇