Today I won the Minnesota Cat 4 State Cycling Road Race championship. A hot and hard day -- over 105F at points according to my Garmin device
Jared Huling
@jaredhuling.bsky.social
Associate Professor of Biostatistics, University of Minnesota https://jaredhuling.org/
I'll never forget coming across this part of his book, it really left an impression on me. Teaching is not only such an important part of what we do as academics, but also truly does have benefits for our own work!
Nice reminder from Richard Feynman of some of the benefits of teaching.
Another important thread from @jeremymberg.bsky.social , this time on data showing nih programs to improve minority access to research careers worked.
Glad to see this story and coverage of an important paper. www.statnews.com/2026/06/17/n... 1/16
Martha Barnard, Jared D. Huling, Julian Wolfson Causal Inference for Functional Treatments with Stochastic Policies https://arxiv.org/abs/2606.27518
@natecohn.bsky.social (the author of this post) reached out to me for some help with it. Energy balancing is a weighting method (similar to entropy balancing) that balances the entire covariate distribution, not just the means. It's described here by @jaredhuling.bsky.social:
degruyter.com
I find this fascinating because my reaction to Dutch suburbs was how wonderful, sane, and livable they are in comparison to suburbs in the US
Academic freedom assessment across the world. The US is on a steep decline, below >120 countries www.scientificamerican.com/article/see-...
With the latest update on CRAN, I've made additional changes to fastglm, including Firth bias correction for all standard GLMs. If you need to fit negative binomial models, try fastglm, as it's much more likely to converge than MASS::glm.nb(), see cran.r-project.org/web/packages...
Negative Binomial Stability Benchmark: fastglm vs MASS
cran.r-project.org
I've made some big changes to the fastglm package with version 0.1.0 on cran: cran.r-project.org/package=fast... - updates that further improve speed - three new models for more complex outcome (neg binom, hurdle, zero infl) - First bias correction - big data support ** Details outlined below:
“You were respectfully informed that distribution of materials [critical of the Trump administration] was not permitted and given the opportunity to remain in the meeting if you stopped handing out the materials. When you continued the behavior, we had no choice but to remove you from the meeting.”
Police Remove Diabetes Experts From Conference for Distributing Critique of Trump Administration
nytimes.com
This is huge. You could have perfectly good cholesterol, do all the right things in terms of diet, exercise and sleep and yet still be at major risk of CVD due to high LP(a). Lots of promising therapies and we'll get to hear whether one of them works this year
"[Novartis, Amgen and Lilly are] developing medicines that lower the level of lipoprotein(a), a fatty particle in the blood that is known as Lp(a)... Tens of millions of people in the U.S. have elevated Lp(a), an inherited and largely hidden driver of heart disease." www.wsj.com/health/pharm...
Always found this type of trick very cute (I guess an instance of 'lifting?):
I've made some big changes to the fastglm package with version 0.1.0 on cran: cran.r-project.org/package=fast... - updates that further improve speed - three new models for more complex outcome (neg binom, hurdle, zero infl) - First bias correction - big data support ** Details outlined below:
fastglm: Fast and Stable Fitting of Generalized Linear Models using 'RcppEigen'
Fits generalized linear models efficiently using 'RcppEigen'. The iteratively reweighted least squares implementation utilizes the step-halving approach of Marschner (2011) <<a href="https://doi.or...
cran.r-project.org
The City of Ottawa posted the raw speed data from before and after Doug Ford banned speed cameras and the effect is so obvious it's not even necessary put a line marking when that happened. This chart shows the percentage of drivers going 15km/h or more over the posted limit.
The Canvas hack is "the biggest student data privacy disaster in history." For years critics have been warning about the centralization of EdTech. Well, millions of students being locked out is what happens when you do exactly that www.404media.co/the-biggest-...
'The Biggest Student Data Privacy Disaster in History': Canvas Hack Shows the Danger of Centralized EdTech
Messages could include "medical circumstances, accessibility accommodations, disputes, sexual assault allegations," and more.
404media.co
I've made some big changes to the fastglm package with version 0.1.0 on cran: cran.r-project.org/package=fast... - updates that further improve speed - three new models for more complex outcome (neg binom, hurdle, zero infl) - First bias correction - big data support ** Details outlined below:
fastglm: Fast and Stable Fitting of Generalized Linear Models using 'RcppEigen'
Fits generalized linear models efficiently using 'RcppEigen'. The iteratively reweighted least squares implementation utilizes the step-halving approach of Marschner (2011) <<a href="https://doi.or...
cran.r-project.org
Paris reduced the number of on-street parking spaces from 140,000 to 70,000 - that is how to enable people-centric neighbourhoods 👍
“Air pollution fell substantially as Paris restricted car traffic and made way for parks, people-streets and bike-lanes.” Better for the climate, better for health, better for livability and quality of life. Common sense. Such a no-brainer, it’s remarkable that more cities HAVEN’T done the same.
I've now in the past two weeks received multiple paper reviews for papers I've submitted that were very obviously written by AI. As a field I think we need to re-assess the role of editors and associate editors in the review process
Just released mori 0.1.0 on CRAN — a new R package for shared memory across processes. Parallel R no longer has to mean duplicating your dataset in every worker's RAM. opensource.posit.co/blog/2026-04... 🧵 1/3
mori: Shared memory for R objects
mori is a new R package for sharing R objects across processes via OS-level shared memory. Parallel workers get zero-copy, lazy ALTREP access to the same physical pages — share once, read anywhere.
opensource.posit.co
#OTD 1878 Kirstine Smith b (d 11 Nov 1939) inventor of optimal designs; her 1918 PhD thesis at UCL described G-optimal designs for polynomial regression. Her work was virtually unnoticed for almost a half-century until its rediscovery by Jack Kiefer in 1959. 1/4 🧵
Although AI improves performance during assisted sessions, performance drops sharply once it's removed. And relative to controls, AI-assisted participants also gave up more frequently on test problems.
🚨New preprint and our results are rather concerning.. We find the "boiling frog" equivalent of AI use. Using large-scale RCTs, we provide *casual* evidence that AI assistance reduces persistence and hurts independent performance. And these effects emerge after just 10–15 minutes of AI use! 1/
(2) If you have ideas related to the role of #statsky, #AI, #realworlddata, or #digitalhealth in policy, we’d love to see them! Please share with your networks. #hpsr #hspr @drjwolfson.bsky.social @jaredhuling.bsky.social @mboudreaux.bsky.social @amstatnews.bsky.social @enar-ibs.bsky.social
ICHPS 2027 Invited Proposal
Please click the link to complete this form.
amstat.jotform.com
🧵(1) @rhubbbstat.bsky.social , @drjasonbrinkley.bsky.social , @lizstuart.bsky.social , @sherrirose.bsky.social , @lucystats.bsky.social , @sarahlotspeich.bsky.social , and I remind you that #hpss is accepting invited session and workshop proposals for #ICHPS2027 by March 31!
The most relieving 6 words that you can ever read in an email:
Another university getting rid of things you could only ever do at a university and replacing them with stuff a 13-year-old can do on a phone
Stories of Grace and what she accomplished have always been deeply inspiring to me!
While working full-time & raising a child, Grace Wahba earned advanced degrees, completing her PhD at Stanford and becoming the first female faculty member in statistics at the University of Wisconsin-Madison. #womenshistorymonth #statwomen magazine.amstat.org/blog/2026/03... #statssky
Interesting paper, especially interesting it's coming from researchers at Anthropic arxiv.org/pdf/2601.20245
Ok, how about this happens at the Minneapolis Orchestra Hall, instead?
Breaking news: Composer Philip Glass withdrew his highly anticipated Symphony No. 15 from its scheduled Kennedy Center performance, saying “the values of the Kennedy Center today are in direct conflict with the message of the Symphony.”