TAS Test @aidanbindoff.bsky.social from @utas.edu.au is a finalist in the Eureka Prize for Excellence in Interdisciplinary Scientific Research. Learn more: youtu.be/lcHGJQmcDjM #EurekaPrizes

1/7 Preprint's live: "Partial pooling predicts cross-validation reliability: a closed-form triage and Rao–Blackwellised cure for hierarchical LOO" arxiv.org/abs/2607.18836 PSIS-LOO fails predictably on hierarchical models. Here's the pattern, and the fix. 🧵

Partial pooling predicts cross-validation reliability: a closed-form triage and Rao-Blackwellised cure for hierarchical LOO

For hierarchical models, Pareto-smoothed importance-sampling leave-one-out cross-validation (PSIS-LOO) fails on the folds where a random-effect coordinate is data-driven and its group is small. We sho...

arxiv.org

If you've ever found yourself questioning the conclusions drawn from PSIS-LOO on a hierarchical model, or facing a multi-day exact LOO-CV, I think you'll appreciate my latest contribution to the #bayesian ecosystem - Rao-Blackwellised LOO with the rbloo package. www.github.com/ABindoff/rbloo

GitHub - ABindoff/rbloo: Rao-Blackwellized leave-one-out cross-validation

Rao-Blackwellized leave-one-out cross-validation. Contribute to ABindoff/rbloo development by creating an account on GitHub.

github.com

Rao-Blackwellizing all the things #bayesian

Very interesting talk by @mendelrandom.bsky.social on the apparent effect of shingles vaccines on dementia. Clear discontinuity from shingles vaccines on shingles, but not on dementia, in this much larger follow up in England, using similar analytic choices as the Wales study that showed a benefit.

George Davey Smith@mendelrandom.bsky.social · 2mo ago

How strong is the evidence that live shingles vaccination prevents the risk of dementia? A talk yesterday @oxprimarycare.bsky.social on this available here youtu.be/qlTnnQytOJ0

Building the smoothbp R package, I had an intuition about what causes funnel pathology in hierarchical models. I was wrong. But chasing that intuition led somewhere more fundamental to the centring vs non-centring decision than I had hoped. New paper: arxiv.org/abs/2606.19655

A Flat Connection: The Pooling Factor and the Geometry of Centring in Hierarchical MCMC

Standard MCMC diagnostics ($\hat{R}$, effective sample size, divergence counts) detect whether a chain has mixed, but not why it has not. We ask whether the centring/non-centring obstruction in hierar...

arxiv.org

arXiv📈🤖 smoothbp: Fast Bayesian Hierarchical Piecewise Regression with Smoothed Transitions and Spike-and-Slab Model Selection By Bindoff

🎉 excited to share: the preprint for smoothbp is now live on arXiv arxiv.org/abs/2606.19044 and v0.1.7 is on its way to CRAN. The package implements smoothed hierarchical breakpoint with spike'n'slab detection for longitudinal Bayesian models. Feedback welcomed. #rstats #bayesian #statistics

smoothbp: Fast Bayesian Hierarchical Piecewise Regression with Smoothed Transitions and Spike-and-Slab Model Selection

Piecewise regression models are essential for identifying structural changes in longitudinal or spatial data across diverse scientific domains. While standard approaches often assume sharp, instantane...

arxiv.org

Fantastic short article on how to understand uncertainty, apparent contradiction, and consensus in science

University of Tasmania@utas.edu.au · 2mo ago

Why should fishers trust science, when it's never certain? Professor Gretta Pecl from @imas-utas.bsky.social says uncertainty is a normal part of science – reflecting how confident we are in the evidence – and shouldn't stand in the way of making informed decisions for the future. More: utas.au/SCA

There's a classic story of Hilbert attending one of Von Neumann's lectures on Hilbert spaces, and Hilbert raising his hand at the end to ask "what is a Hilbert space?" - very relatable as I review my own work on fiber bundle connections in hierarchical models

Is anyone in my network an endorser for STAT.CO on arxiv.org? My co-authors typically submit elsewhere so I'm drawing a blank here #Rstats #Bayesian

smoothbp is now on CRAN! Fit hierarchical piecewise regression models with smoothed change-points, spike-and-slab regularisation, and a Rust-powered sampler — so it's fast. Great for data with structural breaks you want to localise without hard discontinuities (i.e differentiable) #rstats #CRAN

smoothbp has been submitted to CRAN! Hierarchical piecewise regression with smoothed change-points in #RStats - multi-breakpoint models, spike-and-slab regularisation for automatic breakpoint selection, and a fast MCMC sampler written in Rust under the hood. #rstats #statistics #bayesian

Is anyone here a member of fosstodon.org and can send me an invite link? I miss the old twitter back when my feed was all statistics and science

Fosstodon

Fosstodon is an invite only Mastodon instance that is open to those who are interested in technology; particularly free & open source software. If you wish to join, contact us for an invite.

fosstodon.org

If you're using agentic workflows (e.g. Claude) and value reproducibility and transparency, check out github.com/ABindoff/rep... - an MCP server that brings reproducibility logging to AI-assisted scientific computing

GitHub - ABindoff/repro-mcp

Contribute to ABindoff/repro-mcp development by creating an account on GitHub.

github.com

Ladies Cottage, Willow Court, Brigita Ozolins exhibition

Imagine mistakenly drinking cyanide laced Flavor-Aid, thinking it was cyanide laced Kool-Aid? They must have felt so silly when they realized they had been tricked into drinking Flavor-Aid!

Another day, another study using Shapiro-Wilk to assess "normality of data", and not reporting those results (which was fine, because the outcome was dichotomized anyway, because of course it was...)

We're all well aware that "correlation does not imply causation" but few heed this warning when it comes to ratios; indeed you can find them uncritically thrown about almost everywhere

The vibe coding apps are marketing to me so hard rn. The thing is, I have to methodically specify what I need whether I write the functions or AI does it and happily I do that best by ...writing code.

I appreciate that it's staggeringly brazen, but do we think Bondi erred when she claimed to have the Epstein list then later denied it exists? I think this administration is very comfortable with protecting power structures (beyond govt) that they are a part of, and want you to know you don't matter

If you have zero education, this will sound like good advice

Mark Cuban@mcuban.bsky.social · 2y ago

If you have zero education, but learn how to ask AI models the right questions , in many jobs you will be able to outperform someone with an advanced degree, but who is unwilling to use Large Language Models. Just takes a smartphone, curiosity to experiment and a mindset to learn.

So it turns out that compared to centralized distribution of digital information on the web, printed material in libraries provided a kind of distributed defense against the casual whims of an authoritarian government aiming to rewrite history.

AI is an arms race for the world superpowers, and it's certainly not a competition to see who can come up with the best chatbot (like some commenters seem to think)

www.nature.com/articles/s41...

Dendrites endow artificial neural networks with accurate, robust and parameter-efficient learning - Nature Communications

Artificial neural networks, central to deep learning, are powerful but energy-consuming and prone to overfitting. The authors propose a network design inspired by biological dendrites, which offe...

nature.com

Spent a big chunk of the holidays on farm projects including restoring the old hut that stands sentinel at the front of my property