Air travel is so stressful because each time is subtly different from the last so I never know what to expect. Only the baggage scanners on the right work, the others give an error This time, laptop inside the bag for scanning (used to be out) Full body scan? 50/50 chance Shoes off? Who knows

De-anthropomorphizing LLMs via exotic implementations: If LLMs Have Human-Like Attributes, Then So Does Age of Empires II arxiv.org/abs/2605.31514 LLM on a 1979 PDP-11 www.youtube.com/watch?v=OUE3... Via Johan Cedmar-Brandstedt on LinkedIn: www.linkedin.com/posts/johan-...

Reviewing a paper with open data which is great for a change. Downside is that I have to re-install SPSS for the first time in a few years to check the syntax 😞

Here's a kind of broad question, but how do you folks find new interesting content (in any domain) on the internet these days? I feel like a lot of platforms like youtube, spotify, and Bluesky keep me in a closed loop of content that is functionally the same. Search engines are also getting weaker.

So sorry I'm late to the meeting, but Google redesigned the GoogleCalendar icon and now my life is a very small but real percentage worse every day.

I had a student ask me what the "tail" of a distribution is. She kinda looked at me incredulously when I told her it was just the tapered ends of the distribution because it, naturally, looks almost entirely unlike an animal tail and animals don't usually have 2 tails. Honestly, fair critique.

Every time I have to do some statistical method I haven't done for a few years I have to hit the books all over again. There are just so many damned statistical methods to keep straight! This brought to you by trying to remember how to create a predicted probability plot for ordinal regression in R

Apropos of not much, in the 1st year of my PhD at Leeds I was TAing and gave a student a 46 or something for a very, very poor essay. One of the other grad students, who I think fancied her, told her that was too low a mark and on that basis she complained to Seiriol Morgan, the head of 1st year. 1/

I wrote a short paper on methods for handling missed assessments in classes using #stats simulations in R. tldr; Reweighting missed assessments is more equitable than using drop-the-lowest because the latter gives ~2-3 bonus points to students who don't become ill. #edusky doi.org/10.35542/osf...

I was asked to give the commencement speech at convocation for our psychology graduates in June, and while it makes me a little nervous as an uncommon kind of speech, I feel like I can at least manage to not get booed so that is a comfort

Personally I think Jonathan Haidt should be exposed to the challenging perspective that Jonathan Haidt sucks

Toss Your Weasel Wednesday!

Second time I've encountered this reviewing, but people are using a formula to estimate blood alcohol content based on self-report with lots of participants who end up with BAC > 0.5, past the potentially fatal limit. I'm pretty sure ppl didn't fill out your survey if they were dead/in a coma!

More Star Wars equals less dementia. Listen I don’t come up with the figures I just notice the likely entirely unrelated correlations.

Was curious about the analytics of one of my open datasets and seeing 265 downloads is nice but ... only 87 people downloaded the data dictionary. Either people really like to fly blind, or (more likely) just bots.

A new landscape, as usual, Atari 2600 palette, 90s vibes. #pixelart

Good discussion on data sharing and repositories. My take is that AI does mean that we may need to take larger steps to de-identify data if it is open-access; what used to work, may stop working. Combinations of demographic variables and fingerprinting qualitative text may identify folks now.

When did journals start giving only 10 days to review an article? Feels like the deadlines are getting shorter and shorter, which makes me more likely to decline.

This is it: werkenbij.uva.nl/en/vacancies...

I got a high quality article to review for a journal for a change, but it's 90 pages + 50 pages appendicies + 20 pages preregistration + 10 pages protocol + open data and code Have mercy journal gods, I am but one person working for free

I was asked to speak with a graduate class today about research data management. I was asked, "How do people become convinced that beginning data management early on in a project is worth it?" Me: "Suffering. They usual have to suffer first." 😅

This mug should be awarded to every academic who served as department chair.

Gi-normous meta-analysis using individual participant data from international large-scale assessments shows math anxiety negatively related to math achievement. Cognitive & affective facets of math anxiety more negatively related than worry. #PsychSciSky #AcademicSky #EduSky doi.org/10.1037/bul0...

God help me trying to get paid by my own university for a measly $180 of consulting work. It's been 6 months, and I've put in more hours trying to get my money than I actually worked. All I've gotten so far for my effort was them putting my teaching paychque into my business account erroneously.

Someone put a fake server on the Internet and logged everything that came knocking. Fascinating. mastodon.xyz/@soundclamp/...

Significant differences are indicated with 🐦‍⬛

Guess who booked a vacation to Spain in June 💀

As is typical, I thought I could solve my R data formatting problem with a regular expression, so I flailed around for like an hour, despaired at my ignorance, then solved the problem a different way much faster once I gave up.

When I told an AI that the resource it linked me to was written by me, and thus I knew it did not contain the information it claimed it did, it said that was "a real 'I am the Senate' moment". It's not! It was an 'I am Pagliacci' moment, at best. Damn thing couldn't even get that right.

A great learning moment in mentoring a student. She wrote a part in the paper, and just left a blank intending to find a citation to support the point. Then after hours of reading, discovered that the point she was trying to make was actually wrong! Lesson is: Always read first, then write!

Ok #stats people, I want to know your most frivolous use of your data skills. Can only be for the love of the game, can't be for work. I'll start: I record all of my oracle's actions in my tabletop rpg I play (pathfinder 2e), and use ggplot to create data viz of the results like in the attached.

Hey, I wrote a thing about AI in astrophysics ergosphere.blog/posts/the-ma...

This is like asking me where I work, and then me submitting freedom of information requests at every business in town, then doing string match til I find my name in all the replies.

The Orange Cat Brain Atlas is here. 🧠🐈 Today, we published the first comprehensive cellular map of the orange cat brain. The new atlas reveals a single, specialized neuron responsible for behaviors like staring at walls, knocking objects off tables, and the 3am "zoomies."

SCORE, a collaboration of 865 researchers, is now released as three papers in Nature, six preprints, and a lot of data (cos.io/score/). SCORE examined repeatability of findings from the social-behavioral sciences and tested whether human and automated methods could predict replicability.

I got awesome answers to my question from real experts here. Btw, I tried asking Copilot before this to see if I was "missing out" and it: a) Incorrectly proposed that it had no scholarly basis b) Misrepresented citations c) Incorrectly attributed 1st appearance to teaching materials from 2005

Hey #stats people, I'm trying to find the source of something that seems like bad advice, but my students seem to find online. Cooks distance is a measure of influence for outliers. Some people out there recommend 4/N as the cutoff for an influential value. Any idea where this cutoff comes from?

Bayesian SaaS companies and OnlyFans creators are very similar if you think about it🤔 Both make money by showing off their expertly crafted posteriors.

Someone was trying to take a portrait of their two fave Chickens, and this happened.

I am now officially promoted to University Teaching Fellow (like full professor, but for teaching-stream faculty)! 🎉 The true reward is now never needing to collate a file for promotion ever again

Ok this is getting embarrassing for me, so #stats people you know the Akaike information criterion (AIC) right? Uh ... how do you pronounce Akaike? I gotta verbally say it sometimes in teaching, and am tired of making a fool of myself lol

I almost never do any kind of forensic data auditing, but got do spend a bit of time on it in a consulting gig and its ... kinda fun. No maleficence in this case, but folks: Remember to always read the primary sources (someone used a secondary citation of certain numbers, which was wrong).