Frank Harrell

Group performs Beethoven’s symphony No.5 a cappella [🎼 HotPlaysMusic] Original post

IMO simulation based power analysis is the gold standard here -- not because it's better or more accurate (though often...), but because doing it requires knowing enough about the phenomenon you're studying to be able to plug in values that are even remotely reasonable in the first place!

I've updated simulations of performance of various methods for estimating S(t|x) vs. continuous x with right censoring. The new loess method is a winner. fharrell.com/post/kmove #Statistics

Spearheaded by David van Klaveren & with co-authors Peter Austin, Patrick Serruys, @benvancalster.bsky.social our new article in Stat in Med provides a minimal-assumption way to estimate the relationship between survival probability and a continuous variable: onlinelibrary.wiley.com/doi/10.1002/...

fun photo of 5 MB of data on punch cards (from www.lanl.gov/media/public... , via this article on programmer Mary Tsingou en.wikipedia.org/wiki/Mary_Ts... : www.nytimes.com/2026/10/10/s... )

webrarian is a new R package. It turns a folder of R scripts and data into a static website where R runs in the visitor's browser, with no compute server and nothing to install. blog.thecoatlessprofessor.com/posts/introd... #rstats #webr #webassembly

The dark side of the prediction market boom is becoming more clear: Experts say the sites have become go-to outlets for gambling addicts to relapse as the companies avoid state consumer protections. n.pr/4hzSuJ0

I’m pleased to announce that Vol 18 Issue 3 of The R Journal is out now! 🥳 Free & open access, R journal is made possible by our volunteer editors, reviewers + contributing authors. Thank you all! journal.r-project.org/issues/2026-3/ 🧵 20 articles 👇 #rstats journal.r-project.org/issues/2026-3/

I spent 24 years at FDA reviewing the statistics in NDA and BLA submissions. Now I write The Significant Difference: what FDA's reviewers see, and what sponsors need to know. Short, practical, from the reviewer's side of the table. www.thesignificantdifference.com

Could be a game changer for diverging color palettes

Investigative records paint the picture of a professor who took financial and personal advantage of his students for years – from manipulating them into paying him rent to making them clean up after his dog – and grew vengeful when they spoke out about his alleged crimes.

I've been going back and forth between the Zed and Cot editors and have found that I prefer Cot for most things. For the one language I needed syntax highlighting for (Typst) that was not built-in to Cot, Claude quickly wrote the Cot plug-in needed.

Weekend reads: The afterlife of retracted articles; ADA denies it censored opinions; a ‘twisted phantasmagory’ of ghostwriting

Nice paper about ordinal regression and why computing sample means on ordinal data is usually a good idea. #StatsSky #Statistics

Five researchers at Norway’s national gender incongruence clinic are appealing a university committee’s finding they committed “gross negligence” and scientific misconduct after the group published studies using the medical records of more than 1,000 minors.

What a wonderful article about an inspiring collaboration of female mathematicians across the ages. Thanks to @nytimes.com for publishing it www.nytimes.com/2026/09/06/s...

Nice to see coverage of Bayes and ethics --

Excellent @nathanihoff.bsky.social - not only are doubly robust procedures' confidence intervals not robust but point estimates may not be worth the effort. Hope you can compare w/ flexible semiparametric models, which give further advantages to one-step modeling approaches. fharrell.com/post/cpm

Big news! 🎉 𝚖𝚊𝚛𝚐𝚒𝚗𝚊𝚕𝚎𝚏𝚏𝚎𝚌𝚝𝚜 1.0.0 for #Rstats is out. It’s a big number and it feels like a big step. I wrote a blog on the challenges of interpreting statistical models, SPEED, cool new features, the future, and a 5 year package development and writing odyssey. arelbundock.com/posts/margin...

All white, all male. This was unacceptable so recently.

I find it hard to believe that a company like #Google doesn't stick to official names on its maps. They were obscenely quick to respond to the random musings of the tangerine tyrant. Very disappointing

Reread my blog post on the biggest problem in statistics. On re-read, I still don't think it is terrible (other than the typos and things). So I'll repost. timcdlucas.github.io/the-biggest-...

No caption required…

#rstats I'm glad to announce Jarl 0.6.0! Jarl is a very fast R linter, written in Rust. This release brings many improvements and fixes. See the blog post: www.etiennebacher.com/posts/2026-0... And the full changelog: jarl.etiennebacher.com/changelog 🧵 to highlight some features below (1/5)

American Journal of Obstetrics & Gynecology should be ashamed.

A rapidly increasing number of published articles rely on analyses produced via the TriNetX platform. However, TriNetX users don’t get full access to the information in the platform, muddying the truthfulness of any analyses of the data and compromising the integrity statements offered by authors.

If you want to try Gribouille (still in development) for your graphics using the grammar of graphics. I would love some feedback (or bug reports). m.canouil.dev/gribouille/

The more I use @typst.app for producing pdf files (haven't gotten much into html production yet) the more I love it. I'm finishing, with Claude's help, major updates to the #RStats Hmisc and rms packages that add full Typst support.

We invite #RStats users to contribute to a fund dedicated to helping the family of Tomáš Kalibera following his untimely death in April. Find out more and donate here: www.r-project.org/foundation/k...

Highly interesting and important reads, as always.

New Blog post: Which Data Repository Should you Use? In light of OSF closing down, I compare Zenodo, Dataverse, ResearchBox, PsychArchive, and local repositories on six important dimensions. If you want to know which to pick: It depends! daniellakens.blogspot.com/2026/08/whic...

Can everyone stop using the term "real world data" and just be precise about setting, participants and interventions? grandroundsinurology.com/the-reality-...

All four books I've co-authored are freely available online for non-commercial use: - Bayesian Workflow at avehtari.github.io/Bayesian-Wor... Links to other three books are in the quoted post 👇 (too many books to fit in one post!)

What a great review of current Quarto collaboration options by @nrennie.bsky.social

When not assuming a normal distribution is it worthwhile to parametrically fit a distribution? Or better to just go with the empirical cumulative distribution function (ECDF) and its generalization - cumulative prob. ordinal regression? New blog article: fharrell.com/post/ecdf #Statistics #StatsSky

Generally assumed population-based PSA screening = increased overdiagnosis. But already lots of PS testing going on. In a modeling study, we show organized screening would reduce PSA tests, overdiagnsosis compared to current disorganized approach onlinelibrary.wiley.com/doi/10.1002/...

How to avoid the “clean data, clean model” trap when teaching statistics and data science statmodeling.stat.columbia.edu/2026/08/07/h...

This story explains exactly why there is no similarity between the USA under Trump and 1930s Germany. No similarity at all. @larryandpaul.bsky.social youtu.be/z2IdtjKUsX0?...

Another new blog article, elaborating on ordinal regression within the cumulative probability model family. One general model contains an amazing array of special cases used all the time. Do we need to keep teaching special cases&assuming so much? www.fharrell.com/post/cpm/ #Statistics #StatsSky

New blog article proposing a general statement of the fundamental question a standard RCT should answer and providing robust and powerful statistical methods to answer it: www.fharrell.com/post/rctmod/ #Statistics #StatsSky #EpiSky #clinicaltrial #rct #pharma @stephensenn.bsky.social

Weekend reads: Young girl’s death after gene therapy never made public; FDA retracts lettuce test result; ADA delays editorial publication after controversy

Here's a useful page with a **ton** of common tasks in #RStats, done with parallel syntax for tidyverse vs. data.table vs. base. arelbundock.com/posts/dt_tb_... #rdatatable #tidyverse