We've released the first version of our tabpfn #rstats package to CRAN. This is an interface to the Python #TabPFN package.
tidyverse.org/blog/2026/03...
The model is a pre-trained deep learning model that has performed exceedingly well on every data set I've tested it on.
The say “I am alive” comic
I’m reminded of this comic almost every time I check LinkedIn
Many thanks to my amazing co-authors and supervisors @robertboehm.bsky.social and Christoph Fuchs for their work and ongoing support <3
💡 The bigger picture: Workers’ economic expectations of AI vary across countries and are shaped by socio-economic development and culture. This suggests that organizations and policymakers should tailor AI strategies to national contexts rather than rely on one-size-fits-all approaches
In the paper, we discuss potential reasons why this may be the case and report extensive robustness checks, including alternative country-level indicators and different model specifications, across which the main results remain stable.
🔍 Key findings:
- Workers in countries with higher levels of socio-economic development tend to report less positive economic expectations of AI.
- Culture matters: Workers in culturally tighter societies report more positive economic expectations of AI than workers in looser societies.
We find that workers hold positive economic expectations of AI, but there is substantial cross-country variation. In some countries, expectations are more positive, while in others they are closer to neutral or skeptical. To understand these differences, we explore country-level characteristics.
In this paper, we analyze survey data from 14,600+ workers across 31 countries to examine how workers expect AI to affect the economy, the labor market, and their own jobs, and how these expectations of AI’s economic impact vary across countries.
🚀 My first PhD paper is out!
I'm glad to share my first PhD publication: "Country-level differences in socio-economic development and cultural dimensions are associated with workers' economic expectations of AI", published in Computers in Human Behavior Reports (OA: doi.org/10.1016/j.ch...).
Oliver Sacks admitted his case studies in The Man Who Mistook His Wife For A Hat were fraudulent “fairy tales”.
What Psych101 core texts are left?
www.newyorker.com/magazine/202...
Screenshot of the first page of the article, including title "Emphasising herd immunity in vaccine advocacy: a systematic review and meta-analysis", authors and abstract.
Emphasizing herd immunity might be a helpful strategy to improve vaccine uptake 💉 In this meta-analysis, authors found small positive, but heterogenous effects. Interestingly, effects are twice as large for experiential methods, such as VR or simulations!
Read the full paper here: doi.org/qc4j
Tomorrow marks the start of 🌍 World AMR Awareness Week 2025! We’ll be sharing insights from our AMR research as psychologists at @univie.ac.at @ipb.bsky.social @unierfurt.bsky.social and BNITM. Like/share this post for updates throughout the week! #AMR #WorldAMRAwarenessWeek #WAAW2025
Stop being a lame-o and replace dplyr with the more slappin genzplyr.
Ouch
We're hiring! @univie.ac.at is seeking a TT Assistant Professor in the Psychology of Digitalization. If your work is about automation, AI, or immersive technology (e.g., VR) in the context of work and organizations (broadly defined), we’d love to hear from you. 👇
Title: A Justification for 80% Power Abstract: Cohen’s heuristic reason for choosing 80% power (balancing Type I and TypeII errors) conveniently arrives at approximately the same number as an approachwhere one maximizes the marginal gain in power per standard error reduction. Ihave yet to see someone point this out, and this is interesting because it providesa non-arbitrary justification for 80% power.
a derivation of the result
I think this is kind of neat and I don't think anyone else has noticed it (I've looked and I can't find anyone who has) osf.io/preprints/so...
Maybe I should back off "justification" language, but it's at least a remarkable coincidence. I still think someone else *must* have noticed it...
My PhD student @qinyuxiao.bsky.social has written a wonderful tribute to Gary Bornstein’s influential paper on team games (doi.org/10.1207/S153...) — a paper that remains as relevant today as it was over 20 years ago. You can read Qinyu’s short piece here: doi.org/10.1038/s441...
Indeed, your article was by far the easiest to code 🙂. That really reflects the clarity and transparency of your reporting—much appreciated!
Thank you for all the help and guidance! I couldn't ask for a better mentor 🫶
No, Qinyu, you rock 🥹
The article is open access 🔓, preregistered 📑, and fully transparent: we share all data, effect size computations, screenshots of extracted effects, and full analysis code. 🧑💻📂 Just see the post above.
That's all! End of thread! Thanks for your attention <3
Personal note: this is the most work I’ve ever put into a project (yet). I learned so much, and I’m grateful to see it published. With vaccine hesitancy rising, it’s important to remember that every (non-)vaccination also has a social impact
Takeaway 💡
Communicating herd immunity has a small but positive effect on vaccination motivation. However, the effect is larger when people can experience it (VR, simulations) instead of just reading text. 🚀
As such, future messages must be clear, engaging & immersive 🕶️💉
We also ran some fancy machine learning 🧠, multiple tests for publication bias (spoiler: none found ✅), assessed Risk of Bias (all good), and packed in plenty of other cool stuff (including a HUGE table 📊).
For all the details—you’ll have to check out the paper 😉
Among the most relevant moderators, we identify the medium of communication. When people can actually experience herd immunity (e.g., VR, simulations), the effect on vaccination motivation more than doubles (g = 0.29) 🚀
📊 Herd immunity messages do boost vaccination motivation! We find a small but positive summary effect: g = 0.12 (95% CI: 0.08–0.17) 📈 But averages only tell part of the story—what’s even more interesting is when and how these messages work. That’s what we tested next.
To find out, we ran the first systematic review & meta-analysis on herd immunity communication 🧪
🔎 10+ years of experimental work
📂 a whole lot of records screened
📊 43 studies (67 effects), >100k participants
⚙️ Three-level model + Publication Bias Tests + MetaForest
So… what did we discover? 👀
💉 Communicating HI could have different effects:
👉 It could motivate prosocial vaccination (“I’ll vaccinate to protect others”)
👉 But it could also motivate selfish-rational non-vaccination (“I’m safe if others vaccinate”)
Which is it? Does communicating HI help vaccination motivation? 🤔
