Very small contribution of shared environment on adult personality traits probably qualifies?>

Everyone else seems to think we are living in era of unparalleled acceleration, i mostly feel like we're running on the fumes of the past.

Who's been patterning the ferns again?! (UoB Botanical Gardens)

Uh this is great, why am I hearing of this only now.

Now that fake photos and videos are so much easier than, say, climbing into the Himalayas and setting up a trail cam, it's even more worthwhile to block on sight when there's no provenance/attribution.

also llms are often regarded as "stateless," and that's true in a narrow sense, but wrong in a human sense. they're impossibly stateful. it's just all those sedimented states are from at least six months ago. it's the statefulness of the archive and the cemetery.

I'd already br happy if everyone understood randomisation...

Statistical Rethinking 2026 is done: 20 new lectures emphasizing logical and critical statistical workflow, from basics of probability theory to causal inference to reliable computation to sensitivity. It's all free, made just for you. Lecture list and links: github.com/rmcelreath/s...

Psychology has a whole cottage industry in which people come up with some construct that is essentially "attitudes/beliefs/expectations/feelings about X", and then the central claim is that this construct is a super important determinant of future X outcomes.>

One thing growing into my middle age has done has made me much less sympathetic to humanities Takes like this. A pathetic thrill of pseudo-provocation which inevitably backfires when a non trivial proportion of the audience actually just adopt and endorse the stupid read the author was winking at.

Just like a turn to bayesianism doesn’t cure the fundamental problem of statistical illiteracy

Meta-analyses in nutrition may pool estimates for completely incomparable effects without realising it, just because of whether/how energy intake is adjusted. @nataliaortega.bsky.social will explain why, share results from a meta-scientific review & offer recommendations for ways forward 👇

"My name may be forgotten when it comes, but the time will arrive when great outbreaks of cholera will be things of the past. And it is the knowledge of the way in which the disease is propagated which will cause them to disappear" Happy birthday to John Snow! His name & his work is not forgotten.

Research in a nutshell. Politics in a nutshell. Human societies, in a nutshell. We only progress because these misunderstandings are ironed out in a long and noisy message passing process over uncountable iterations and large populations with important information only slowly trickling through.

That's why I'm so against ChatGPT. I'm against letting a machine do your homework for you. I think you should cling to Doing Your Homework Yourself like it's the last opportunity you have to liberate yourself from mental enslavement. Because it basically is. Anyway shout out to Kai Cenat.

I think a lot of us millennials & older really take it for granted that we were the last of only a couple generations where there was an all-encompassing campaign to encourage literacy. Everyone used to agree upon it. There were commercials with your favorite celebrities just being like, "READ!"

I really like Devezer's comments. Unfortunately couldn't keep myself from reading the original substack post: Going to "These are solvable engineering and institutional design problems" from "How do we verify AI-generated claims at scale?" is just... I honestly don't have a word for that.

2. Of course we should hold AI to the highest standards. That doesn't imply double standards because we can treat AI as technology without anthropomorphizing it and we primarily conceptualize science as a human endeavor. The two can be subjected to different standards. It's normal, not at all weird.

Really super legible 🤯 (I assume it can also be used in less optimal ways...)

Exactly this. Burning a generation for some weird company bets.

I'm constantly trying (/failing) to get this point across. If you're a trained expert in a field, then it may be worthwhile to question the scientific consensus of your peers. If you're not, the scientific consensus is absolutely the best you can do and it's arbitrary foolishness to disregard it.

These seminars are always worth it, and what's fantastic on top: when you have to suddenly run halfway through a talk the recordings are freely available!

Longevity influencers tell millions to take rapamycin, sit in hyperbaric oxygen chambers, blast themselves with red light therapy, and take 50+ supplements daily. Meanwhile something that cuts dementia risk by 20% is invisible. overmatter.substack.com/p/your-anti-...

Saving this for teaching...

New YouTube video posted “The Joy of Coupling” Happy Valentine’s Day! youtu.be/rpW2ZYtXn6o?...

"Model to Meaning" just received a super generous review in JASA. Check it out! (I'm blushing 😊) Reminder: You can get the paper copy from CRC, and the full **free** version will remain online forever at marginaleffects.com www.tandfonline.com/doi/full/10....

Neyman is my hero

chronometre: A new package (pair) demo for R and Python Efficient yet simple object exchange between R and Python dirk.eddelbuettel.com/blog/2026/02... #rstats #rcpp #python #datascience

I made a filterlist for uBlock Origin to remove Generative AI features on websites. Includes blocks for * Google AI Summaries * YouTube Ask button & chat summaries * GitHub Copilot * Facebook AI chat * X's Grok buttons * Deviantart DreamUp * Booru AI images * And more github.com/Stevoisiak/S...

It lives! 🎉 dx.doi.org/10.1002/sim.... Quite some time ago I mentioned the arxiv version of this paper comparing imputation, raking, and TMLE in a reasonably large set of simulations, by authors including moderately strong partisans of the various approaches.

As Rotten Tomatoes might be getting astroturfed, a quick quiz: - Amazon paid $40 million to make it - Amazon paying $35 million to promote it - Amazon own IMDB What is going to be the opening score at IMDB?

Everytime some asshole starts taking about how "EU regulation stifles innovation", this is the kind of stuff they are hoping to enable.

Then prove it!! Where is the evidence!? Where are the evaluations!?

Fantastic talk, a must see!

Info, schedule, and recordings: cls-data.github.io/CIIG/ Join mailing list: www.jiscmail.ac.uk/cgi-bin/wa-j...

If you are interested in all things ✨causal inference✨, please join our multidisciplinary Causal Inference Interest Group (CIIG). We host monthly seminars featuring speakers with various academic backgrounds and research interests. Links below. cc @clscohorts.bsky.social @pwgtennant.bsky.social

Woah terrible, glad to be on Fedora here.... Also good description on how to think of a quick local fix.

I think that the mass enthusiasm we see around gen AI is manufactured, and I think this because it doesn't exist for renewable energy, despite it being more measurably impactful (and also technologically wonderous)

In which I look at simulations to see how well a Normal distribution fits something, but with complications notstatschat.rbind.io/2026/01/05/s...

This smells distinctly like collider bias and/or selection bias and/or regression to the mean... You simply can't select teen prodigies, and world class athletes rom databases, and go run regressions without serious consideration of the selection process!

Historic Austrian cartographer Freytag&Berndt is sadly closing their bookshop in the center of Vienna for good on the 24th. A good time to post this data visualisation classic. @datavisfriendly.bsky.social

ANNOUNCE: #dataviz #rstats #psy6136 📊 This winter I'm teaching a new instance of my course on Categorical Data Analysis, featuring analysis and visualization methods for frequency data and model-based methods (loglinear models, logistic/Possion regression).

Episode 527 of why you never want to rely on a commerical service to host something for you 'forever'. As many people have eloquently stated before, better to register your own domain for control (at ~ $10/year) and use hosting at GitHub Pages, Netlify, Cloudflare, ... #rstats #digitallife

I've spent all day struggling to write a single page of a popular science article. I bang away at a word processor; give up; start diagramming on paper. Take some notes; draft a few sentences in pen; return to the computer...and very slowly I figure out what I was trying to say in the first place.

This. Very interesting thread.

I always briefly tell my students about libs like BLAS etc. And when they ask me what they need to know: well, just that they exist and are important is a good starting point 😅

I am tremendously grateful for open source, as it’s had such a huge impact on my career. That’s one of the reasons I’m so happy that Posit has committed to the @opensourcepledge.com. Read about our contributions to non Posit projects at posit.co/blog/posit-o....

web search results are such a wasteland now and I hate it I miss finding cool information on websites that were clearly personal passion projects, or giant FAQs formatted in pure ASCII that explained everything about a niche topic

Fifteen Years xkcd.com/3172/

Dear Lord 🥺