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/...
Close up with a beautiful nudibranch on a rocky reef. The lower half of the image is a palette of swatches made from the nudi's vibrant colours.
Once upon a time I just admired nudis and sea slugs.
But it was not enough. Now apparently I'm creating an R package to celebrate their colour palettes? 😅
First up, my Sydney fave, Hypselodoris bennetti.
#rstats #nudibranch #dataviz 🦑🐙🧪 #marinelife #invertebrates
Nice clear presentation of commonplace meta-analysis failure mode: Pooling coefficients that mean different things, because original models had different adjustment sets. A coefficient gets its meaning from the whole model, not just from the predictor variable it multiplies.
Top down view of a Bullina bubble snail exploring algal turf on a shallow rocky reef. Two tiny black dots for eye-spots behind its headshield. Neon blue edge, a pale blue body, cherry-red stripes on a tiny white shell. What's not to love. Lower half of the image is swatches of the Bullina's colours.
Last of the palettes included in the R package, but certainly not least, the beautiful Bullina bubble-baby. Tiny, friend-shaped, perfect.
#rstats #dataviz 🦑🐙🧪 #marinelife #invertebrates
Brief fun survey from Jessica, Andrew & myself:
If you are a faculty member, research scientist, postdoc, or senior Ph.D. student in any area of science, please take five minutes and fill it out. We’ll share the results widely along with some reflections.
docs.google.com/forms/d/e/1F...
Super interesting reading the definitions for the candidate epistemic virtues for science inquiry
(have narrowed my picks but still ranking them...& not sure when this survey closes...)
holy shit
Bird nests made from anti-bird spikes?! 🤯
Hi, I'm a nest researcher 👋 and new here on BlueSky, sharing the craziest #bird nests I've ever found. 👀 Today, I’m sharing my discovery of rebellious birds that build nests out of anti-bird spikes. And honestly, it's like telling a joke...
A thread. 🧵
Magpies’ nest made from anti-bird spikes and a strip of the spikes (bottom right). Photograph: Auke-Florian Hiemstra / Naturalis Biodiversity Center It is an impressively large nest
Magpies are absolute superstars for this artform:
Magpies’ nest made from anti-bird spikes and a strip of the spikes (bottom right). Photograph: Auke-Florian Hiemstra / Naturalis Biodiversity Center
'When the current Prime Minister of the United Kingdom makes a bad decision it always seems that others must take the blame.' Excellent summary of the increasing political weakness of Starmer's position over Mandelson @davidallengreen.bsky.social emptycity.substack.com/p/the-decisi...
Wildlife trade drives animal-to-human pathogen transmission over 40 years
New in @science.org ‼️ In the most comprehensive study to date, we show that wildlife trade is driving animal-to-human zoonotic spillover at a planetary scale, with +1 spillover per host every 10 years. Live animal markets and illegal trade pose even greater risks. 🔓 www.science.org/doi/10.1126/...
TRUMP, throwing insults at Pope Leo:
“weak on crime”
“terrible for foreign policy”
“catering to the Radical Left”
“owes his position to me”
“sit down and mind your own business”
POPE LEO, unbothered:
“We are called to love.”
I'll send the link when I'm at my desk 👍. It's really not my field but people in the disability sphere have got me thinking (better late than never I suppose). The thing that really hit home is the adoption of copilot at my university in the name of "productivity". I mean, define productivity!
An interactive OJS playground demonstrating a linear congruential generator (LCG) using the formula X_n = (aX_{n-1} + c) mod m. Controls on the left set modulus (m=8), multiplier (a=5), increment (c=3), seed (X_0=1), and numbers to generate (12). A table on the right shows the resulting sequence of X values, intermediate calculations, mod m results, and normalized values X_n/m, with the final "random" numbers highlighted in yellow.
Excerpt from the blog post with R code that tests all seeds from 1 to 10,000 to find which ones produce 10 heads in a row when simulating coin flips. The possible_seeds data frame is filtered to show 10 seeds (614, 1667, 3212, 4166, 4580, 5527, 5824, 7365, 7468, 8975) that meet this criterion. The post notes that seed 614 actually produces 13 heads in a row, confirmed with a withr::with_seed(614, ...) call below.
R console output demonstrating that set.seed(1234) produces reproducible results. The first block calls runif(5) and returns five values: 0.1137, 0.6223, 0.6093, 0.6234, 0.8609. The second block uses the same seed but splits the draw into runif(2) then runif(3), returning the same five values in the same order, showing that the sequence is preserved regardless of how many numbers are drawn at a time.
Table of contents for the post: Introduction Seeds and reproducible randomness My (somewhat incorrect) mental model of how seeds work Making “random” numbers with an equation Live interactive playground Cycles and fancier algorithms Why does it matter if “random” numbers aren’t actually random? You’re limiting yourself to narrow, known universes You can seed hack and get any values you want Real world bad things can happen because of pseudorandom numbers Can computers even create true randomness? Moving a mouse around Lava lamps Atmospheric noise How I use true randomness in my own work “…as an ook cometh of a litel spyr…”
I've been using random seeds for years but I have no idea how they work. Seeds somehow(?) make the same random numbers?
So I figured it out! New post includes an interactive PRNG generator, lava lamps, lottery fraud, @random.org, Chaucer, and Minecraft #rstats
www.andrewheiss.com/blog/2026/04...
Looks fantastically useful
How to join zillions of lexical norms to each word in your language sample the easy way: a quick tutorial and demo reilly-lab.github.io/Jamie_JoinLe...
If your Bayesian solution ends up with the same uncertainty under both scenarios you are maybe not taking your generative mechanism seriously enough. I (by which I mean Lauren) wrote about this once in a paper that didn’t get as much love as the worse one I wrote before arxiv.org/abs/1905.10341
cover of the book "Bayesian Workflow" by Gelman, Vehtari, et al. Coming out later this year, in the summer probably.
I would have preferred to have the "draw the rest of the owl" meme on the cover, but this will do. Seems like it is on schedule, and we'll leave some typos so you know we didn't write it with AI.
More details about the Bayesian Workflow book and case studies now available on the book web site avehtari.github.io/Bayesian-Wor... (but you still need to wait a bit for the book)
- Replicability is not estimated consistently across studies. Different estimates have different properties and interpretations. Estimates vary greatly depending on the choice of replicability metric.
- Replications do not track truth but I've written a lot about this elsewhere so I'll stop here.
I could recommend these four papers of ours for starters:
1. journals.plos.org/plosone/arti...
2. royalsocietypublishing.org/doi/abs/10.1...
3. royalsocietypublishing.org/doi/abs/10.1...
4. philsci-archive.pitt.edu/24738/
OK for fun: top funniest tweet ever? I am torn between "moon's haunted" and "Denise I was at your wedding."
I built a Quarto extension that adds accessibility features to Reveal.js presentations: keyboard nav, screen reader support, dyslexia-friendly fonts, high contrast, slide change visual/audio cue and more.
Feedback more than welcome.
github.com/mcanouil/qua...
#Quarto #RevealJS #Accessibility
Part 2 of my shrinkage estimator series is out! Part 1 covered the univariate case, but now we dive into multivariate shrinkage 🤓
We cover Spearman's classic correlation disattenuation formula, multivariate James-Stein estimators, and hierarchical methods too
haines-lab.com/post/how-to-...
This is basically how my personal development meetings go. I say to my students: there’s room in the world for everyone. There should be
Photograph of a car with a squirrel inside of it, perched on the steering wheel. The car is the color of champaign at a beige convention, and the squirrel is the color of squirrels. The squirrel is holding a package of crackers in it's mouth. They are the kind like you get at a restaurant, where you get two crackers wrapped in plastic. The driver's side window is slightly cracked. This is how the squirrel got in, and how it got out. It threw the crackers out first, and then climbed out after them. Everything in this operation suggested that this was not the squirrel's first rodeo.
A closeup of the squirrel sitting on the steering wheel. The squirrel deserves a name, so we'll call her Anjeloma, and she's what you might call a winner. She is still squirrel colored. The crackers are white, and labeled "Zest." As if Anjeloma needed more zest. Squirrel, please. You can't see much of the car, but you can see smudges of grunge at the edges of the windshield, where the wipers have cast aside the debris of previous rains and pollen-falls.
The world is stupid, but I just watched a squirrel break into a car in the parking lot below me, steal a package of crackers, and escape to a nearby tree. So at least somebody is winning.
Great to see this! Learn more about the different ways to easily reuse our data, with our Chart Data API and enhanced data downloads: ourworldindata.org/easier-to-re...
Code Window 1.0.0 for Quarto is here.
Add window-style decorations to your code blocks: macOS traffic lights, Windows buttons, or a plain title bar.
Hotfixes: Filename and code-annotations for Typst/PDF in Quarto 1.9.
github.com/mcanouil/quarto-code-window
#Quarto #Typst #TechnicalWriting
For those deterred by the (free) registration link, here's the full piece:
