How to report a N=12 study?
statmodeling.stat.columbia.edu/2026/04/14/h...

I always enjoy Honours talks. So much cool science in a short time. Ecology, geology, organic chemistry, dinosaurs, neuroscience. Its great.

we like to provide a real farm-to-table artisanal data processing experience

I mean, it's completely fine to say there's a 95% chance that a tibble will not behave as a data frame.

(you can't deny that this was an epic example, incorporating baseR-tidyverse flamewar with frequentist-CI-interpretation-controversial)

Being able to use a lookup table & just use "from" & "to" language like this is SUCH a wonderfully change for me when recoding values 🥹 #dplyr has always felt conversational to me, & now we can finally use it to say "recode this variable from this to that" without typing a long case_when #rstats

The full making-of recorded with {camcorder} in #RStats 📹 🧵4/5

This is exactly the function I needed this afternoon and I only knew it existed because I remembered seeing this. Social media works!

Two plots side by side showing time in weeks on x axis and probability of returning to work on the y axis. The left hand plot shows the trajectory of two groups (self-efficacy improved or not improved), while the right hand plot shows the probability difference between the two groups.

geomtextpath can really help make a plot easier to interpret. Nice to avoid using a legend. #rstats #dataviz

An example, here asking to recreate in LaTeX the definition of a pseudorandom number generator

In case you aren't already aware of one of the nerdiest, nich-est online games: TeXnique, where the goal is to type LaTeX formulae as quickly as possible. texnique.xyz

It is "fun."

When plotting, LLMs see what they expect to see - Posit Data science agents need to accurately read plots even when the content contradicts their expectations. Our testing shows today's LLMs still struggle here.

Introducing bluffbench, a new tool to evaluate how well LLMs actually see data plots.

When we trick LLMs with secret #RStats transformations, they can miss the visual contradiction.

bluffbench helps us measure this "blind spot" in AI coding agents. Learn more: posit.co/blog/introdu...

#rstats
🌈🌈 Do you ever need/want to print text in color in markdown/Quarto documents, so you can easily refer to red points or blue lines in a graph?
A start on this is in the {colorize} 📦, friendly.github.io/colorize/

(Kangaroos on campus is normal but not quite like this)

A path with bushes on either side. A kangaroo is barely visible amongst the bushes.

🦘 certainly well camouflaged

Yeah I think if you had an institutional account and ran your whole class through it that'd be quite effective. I think I'd have some trouble getting IT approval, and most students manage to install Rstudio on their own computers so it'd be a lot of logistics just for the edge cases.

We send the cursed ones to use posit.cloud free accounts but I wish there was a nicer solution

Kanji Explorer available at https://jcarroll.shinyapps.io/kanjiexplorer/

I Vibe Coded an R Package
and it ... actually works?!?

jcarroll.com.au/2025/09/13/i-vibe-coded-...

I wanted an #rstats package to exist so I spent $20 and got Claude Code to build it for me.

Plus a shiny app using it: https://jcarroll.shinyapps.io/kanjiexplorer/

my lil reproducibility talk from today / I really wanted to instill the PhD students some simple first practices and ways to step up your game from there github.com/tjmahr/2025-...

Wow. The discussions in the Annals of Statistics were... rough, in the 80s 😅

That being said, interesting paper and discussion. (Thanks to Yannis Yatracos who sent me this reference!)

Scientists uncover the secret lives of dugongs in Moreton Bay The world's largest health study of dugongs in Moreton Bay provides critical clues for helping conserve the enigmatic marine mammal, especially in other locations where numbers are falling.

Dugongs!! This is a great article. I was lucky to be part of this team in the distant past so it's great they are still doing cool science

Job alert: 2.75 -3 yr postdoc in Mathematical ecology/epidemiology or Decision Sci at the University of Queensland on the value of information for decisions with @hugepossum.bsky.social @katehelmstedt.bsky.social Katriona Shea & myself #MathSky 🌍 uq.wd3.myworkdayjobs.com/uqcareers/jo... please share

Happy to discover that R.A. Fisher already relied on what one may refer to as "resolution by cope"

Graphical abstract for "Vocal communication is seasonal in social groups of wild, free-living house mice." The abstract has, from top to bottom, a title, four middle image panels, and two bottom text panels. Image title: "Vocal communication in social groups of wild-free living house mice" Middle image panels from left to right: (1) An aerial snap shot of the region where the study site is located, an agricultural landscape in rural Switzerland. (2) An image of the study site, a small barn in the forest inhabited by mice. (3) An image of a radio frequency identification (RFID) box used to track mouse social interactions. A mouse is entering the box from the left while another sits outside. (4) A spectrogram showing example vocalizations - one low frequency squeak and one ultrasonic call - recorded from an RFID box. Bottom panels: Left: Data Collection  - 10 years of RFID-based tracking data (from 6,946 mice) - 15 months of acoustic monitoring (totaling 6,594 hours) - Machine learning for vocal detection and labeling (CNN) Right: Key Findings - Vocalization is seasonal (most in spring and summer) - Vocalization is associated with the presence of pups - Vocalization is correlated with social group dynamics

Very happy to share the latest from my postdoc‬!

10 yrs of mouse social networks + 1.25 yrs of acoustic data ➡️ insight into vocalization & sociality in a wild population of your favorite lab model 🐁

paper: bit.ly/4n93yyD
data: bit.ly/4lfFBEk
code: bit.ly/4kNnMwx

#bioacoustics #neuroskyence

1/8

Little Ume, our endangered tapir calf, has loved meeting so many of you over the past two weekends! 🩷 This growing baby needs lots of rest, so she’s been catching plenty of zzz’s behind the scenes and in her habitat. 😴

Please share. 2 tenure-track T&R math/stat jobs at the University of Queensland, Australia. Amazing weather, gorgeous campus & lifestyle. 17% employer retirement contribution, lots of leave. Strong global reputation. Supports diversity @stevenstrogatz.com uq.wd3.myworkdayjobs.com/en-US/uqcare...

Sorry, Modsim!

Should I go to the Australian Statistical Conference or Modism?!? They both look cool but are in direct competition...

Converting R data-wrangling code to julia YouTube video by JuliaHub

🔥🔥🔥

Check out this Tidier.jl (and general #julialang data) tutorial from @kevinbonham.com @juliahub.bsky.social!

#rstats #tidyverse

youtu.be/bw-N1lrDeHI?...

Sum-score effect sizes for multilevel Bayesian cumulative probit models | A. Solomon Kurz This is a follow-up to my earlier post, *Notes on the Bayesian cumulative probit*. This time, the topic we're addressing is: *After you fit a full multilevel Bayesian cumulative probit model of severa...

If I'm following correctly, you can do this as a Bayesian with brms like so: solomonkurz.netlify.app/blog/2022-07...

Lecturer: Mathematical Sciences (Academic Level B) Job in Mawson Lakes, Adelaide SA - SEEK Contribute to research in Mathematical Sciences focusing on Applied Mathematics including dynamics, modelling & computation

2-year lecturer position in our Applied Maths / Modelling / Computation group at Uni SA / Adelaide Uni - www.seek.com.au/job/83327354

Causal Inference With Observational Data and Unobserved Confounding Variables As ecology tackles progressively larger problems, we are moving beyond the scales at which randomised controlled experiments are feasible. Using observational data for causal inference raises the pro...

OK, #causalinference #ecology folk - my paper with the even excellent @lauradee.bsky.social on causal inference with observational data is now out in Ecology Letters! 🌍🧪🌊

onlinelibrary.wiley.com/doi/full/10....