Fascinating that Galileo's reputation as a "big ideas" scientist (and they don't get much bigger than Galilean relativity, principle of equivalence, and light having a speed) can be broadened by the finding he was also on top of the details/maths. www.science.org/content/arti...

Except literally every data analysis or model I've ever asked AI to build has contained at least one error: www.nature.com/articles/d41... Common response: "But someone just needs to give AI detailed instructions..." But who is the "someone" in that sentence? And how did they get their expertise?

I'm so excited to announce the first release of my newest #Rstats package, {adrftools}! This package facilitates estimation, visualization, and testing for the causal effect of a continuous (i.e., non-discrete) treatment. 🧵 1/10 #statssky #episky #causalinference

Job offer: PhD-level biostatistician with ML&omics experience to work on prediction models for CAR T cell therapy, in an exciting clinical trial - spatial omics - data science consortium (LOOP/INTeRCePT3.0 centered in Zurich; this position in Heidelberg) embl.wd103.myworkdayjobs.com/en-GB/EMBL/j...

“It is a fault to wish to be understood before we have made ourselves clear to ourselves.” — Simone Weil, Gravity and Grace

Hannah Arendt did not mince words, did she? 'Totalitarianism replaces all first-rate talents with crackpots and fools whose lack of intelligence and creativity is still the best guarantee of their loyalty.' From "The Origins of Totalitarianism" (1951)

“Selfish — a judgment readily passed by those who have never tested their own power of sacrifice.” — George Eliot, Silas Marner

Would love to see more people on LinkedIn with 'non-strategic leader and non-systems thinker' in their bio. Like, just really focused on tactical execution and solving specific things reliably.

Last Christmas I gave you my heart. The very next day You gave it a weigh.

Cool. Classical billiards can compute - but only "for some value of billiard table" I think. arxiv.org/abs/2512.19156

I cannot be trusted to attend a meeting without a calendar invite

MIT's famous 'Missing Semester' course (for the Independent Activities Period in January is back. missing.csail.mit.edu/2026/

Why does anyone use the Wilcoxon test for anything? It's not even transitive. It's sensitive to things one most likely is not looking for (changes in distribution shape) and relatively insensitive to what one usually is looking for (change in location). www.sciencedirect.com/science/arti...

How popular AI apps produce a non-scientist’s idea of quality science kucharski.substack.com/p/the-shallo...

How does immunotherapy work, and why do some patients respond while others don’t? Book our free talk by Samra Turajlic, head of the Cancer Dynamics Lab here at the Crick, Director of @cruk-mi.bsky.social and head of the UK-wide MANIFEST programme. www.eventbrite.co.uk/e/crick-cras...

In honor of National Poetry Day, the greatest parody rewrite of all time:

Am contributing to a collaborative dry-wet project proposal and everyone incl. myself thinks I should be writing about fancy algorithms. Instead, I spend all time on experimental design,power, what do we know or not, what do we aim to show? And on 2nd thought, that's probably OK for a statistician.

Listen to our director Edith Heard on BBC Radio 4 Woman’s Hour - discussing her career, working with AI and the importance of attracting the best global scientific talent to the UK. www.bbc.co.uk/sounds/play/...

Listen to Sonia Gandhi, Assistant Research Director at the Crick, on the latest episode of BBC 4’s The Life Scientific. Sonia discusses her lab’s use of stem cells to drive the development of drugs and other therapies for Parkinson’s patients. www.bbc.co.uk/programmes/m...

So often there’s a gulf between knowing (a particular aspect of) a topic and understanding it from multiple perspectives. Like the analogy here to matrices vs linear algebra.

Exciting day for @crick.ac.uk today: Edith Heard takes over as Director We're looking forward to this new chapter in the story www.crick.ac.uk/about-us/lea...

We didn't randomize, and there was no allocation concealment or blinding, and we can't really be sure what intervention they got or how the outcomes were measured, but we emulated a trial by drawing a DAG.

Just finished The Names by @florenceknapp.bsky.social What a heart-wrenching story, beautifully structured and shining with empathy. One to ‘cherish’

For the math folks on here: NSF has suspended Terry Tao's grant. www.nsf.gov/awardsearch/...

Time for your yearly reminder that “We need less research, better research, and research done for the right reasons”. #OTD 1948 Douglas Altman b (d 3 June 2018) “One of the most influential medical statisticians of the past 50 years” he led reforms in medical research reliability & reporting. 1/3

AI slows down experienced developers (against their expectations) in a randomized controlled trial of AI coding effectiveness. metr.org/Early_2025_A...

Join @dremmacbw.bsky.social, a Senior Clinical Research Fellow at the Crick as she explains how her team are working to improve understanding of the biology of long COVID and discovering new ways to both prevent and treat this complex disease. www.youtube.com/watch?v=JMNe...

Congratulations to the Crick’s Samra Turajlić on her new appointment as Director of the @cruk-mi.bsky.social 🥂

"Why worry about your privacy If you aren't doing anything wrong?"

Good Science xkcd.com/3101/

"Since her death in 1979, the woman who discovered what the universe is made of has not so much as received a memorial plaque. Her newspaper obituaries do not mention her greatest discovery. LET ME TELL YOU ABOUT CECILIA PAYNE:" #WomenInScience #WomenInSTEM #History 1/8

Starting to look like I might not be able to work at Harvard anymore due to recent funding cuts. If you know of any open statistical consulting positions that support remote work or are NYC-based, please reach out! 😅

Every week I'm reminded of how measurement, statistics, design, bias and error are so often treated as sidecars to "the science" in clinical research. It seems like the funders are coming around on this, which is great. Will institutions respond by investing in methods expertise?

🚨 Next month, we’ll be hosting a one-day event on target-trial emulation and other frameworks, exploring the role and potential of observational data for evaluating the effects of interventions Open to everyone working in #datascience #biostatistics #clinicaltrials Get your ticket 🔽 bit.ly/TTE_25

Private meeting: conclave Public meeting: convlex

I’d counter by having pensioners sent to classes on climate change, trade economics and the histories of slavery and colonialism. Two can play at this game.

The problem with this study is not confounding. The problem is that it is a meaningless 'risk factor association study'. The results cannot be interpreted. The study has zero scientific or practical value. Such studies need to be outlawed for undermining faith in science.

HIRING! We offer 3 fully funded PhD positions to work on research methodology with experts in a great medical research environment. More info: www.linkedin.com/feed/update/...

“Scale vs Scrutiny” beautifully sums up an aspect the grey zone between statistics and data science.

FACT CHECK: This viral graph from twitter claims to *prove* vaccines cause autism. But there's something fishy about the data! Let's dive in.

“There are three classes of men; lovers of wisdom, lovers of honor, and lovers of gain.” — Plato, Republic

Causal inference is to statistics as statistics is to math. Many mathematicians think they know all there is to know about statistics but would struggle to do the work of a statistician.

Measles.

Publishing the (nonsense) tariff formula unfortunately seems like quite a shrewd move, because it has got lots of people arguing over a devastating, poverty-inflicting policy in the most boring, unengaging way possible…

End a clinical trial early, and researchers might not be able to tell if it worked, leaving participants worse off than when they started. But that is what the Trump administration is asking scientists to do, @katherinejwu.com reports.

My issue with reasoning agents doing evidence synthesis is that most empirical statements should be dismissed. Even in reputed journals. Because most numbers in frontiers need to be revised and nobody does that for papers 10 years old. DM me if you want to collaborate on this. #MetaSky #StatSky.

I (and Lebesgue) am surprised that everyone chose integers.

it is grimly hilarious that, given the immense, decades-long fetishization of "leadership" and "leadership skills" in business-oriented academia and politics, even unto the formation of leadership institutes, there should turn out to be no leaders in any positions of power