Sign in

Darren Dahly

@statsepi.bsky.social
14K followers 2.7K following 7.4K posts

Epidemiologist + Statistician | Clinical Research Facility - University College Cork | UCC School of Public Health | #ClinicalTrials #Epidemiology #Statistics #RStats Posts not for everyone ¯\_(ツ)_/¯ Views mine -> statsepi.substack.com

PostsRepliesMedia
Darren Dahly @statsepi.bsky.social · 14h
Sorry, while I have you here, I might also suggest that the methods and incentives for creating new knowledge can be very different from those used to create innovations.
020
Darren Dahly @statsepi.bsky.social · 14h
"Innovation" and "new knowledge" are not synonyms! That is all. Thank you.
170
Darren Dahly @statsepi.bsky.social · 16h
Not exactly scary, but I was somehow allowed to watch the Elephant Man by myself at night when I was about 5 or 6. Profoundly sad and I've probably never cried that hard, before or since. en.wikipedia.org/wiki/The_Ele...
en.wikipedia.org
The Elephant Man (1980 film) - Wikipedia
281
Darren Dahly @statsepi.bsky.social · 18h
lmao
081
Reposted by Darren Dahly
James Balamuta @coatless.bsky.social · 04/10/2026
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
A card for the R package webrarian. Large text reads "A folder in. A website out." On the left, a small card lists a folder named lab-01 holding lab.R, setup.R and a data folder. A red arrow points from it to a browser window that shows a scatterplot of car weight against miles per gallon with brick-red points. The address coatless-wasm.github.io/webrarian is on the card.
414860
Darren Dahly @statsepi.bsky.social · 19h
Looking forward to seeing my fellow IFUT members today on the quad for a one hour work stoppage in pursuit of a credible pay proposition from government. www.ifut.ie/content/ifut...
081
Reposted by Darren Dahly
Richard Sever @richardsever.bsky.social · 03/10/2026
And your regular reminder of the innumeracy of this metric (a pseudo mean calculated from two different datasets and applied to a non-normal distribution) www.biorxiv.org/content/10.1...
34311
Darren Dahly @statsepi.bsky.social · 05/10/2026
Which is just to say that in medicine, we can see how useful non-representative RCTs can be.
040
Darren Dahly @statsepi.bsky.social · 05/10/2026
"Similarly, there are many medical interventions that have been brought to market on the back of RCT evidence that indeed panned out to be widely effective treatments. One could even argue that non-representative trials producing widely generaliz- able results are a key driver of medical progress."
fertstert.org
140
Darren Dahly @statsepi.bsky.social · 04/10/2026
🫠
000
Darren Dahly @statsepi.bsky.social · 04/10/2026
bsky.app/profile/abeb...
100
Reposted by Darren Dahly
Dr Abeba Birhane @abeba.blacksky.app · 07/05/2026
a new investigative journalism audit of the Kenyan SHA system-AI that calculates affordability for access to healthcare-just dropped & its scandalous "The AI income predictor systematically overcharged those who could least afford it while undercharging the well-off" sha.africauncensored.online
sha.africauncensored.online
Hiding Behind AI
How SHA Was Used to Load Health System Costs Onto Poorest.
611865
Reposted by Darren Dahly
Julia M. Rohrer @dingdingpeng.the100.ci · 04/10/2026
This is very good. “Over 2.2 million cancer deaths can be attributed to Costco; that’s more than 20% of all cancer deaths between 2000 and 2018.”
Ridiculous things you can “prove” caused cancer mortality

Everything causes cancer. Sounds cliché; maybe those California warning tags were right all along. But thanks to the methodology created by Alwadi et al., we can now prove that anything and everything causes cancer. Oh, sorry, that is too strong of an assertion. To use the authors’ words, since they have claimed their papers don’t prove causality, we can create an association between any physical landmark and cancer and, from that association, figure out how much cancer is attributable to that thing. Which is totally not the same as saying “that thing causes cancer.”

For instance, living near a private four-year university is associated with a 15-fold increase in cancer mortality when compared
1111423
Reposted by Darren Dahly
Joe Noonan @joenoonan.bsky.social · 03/10/2026
'Israel, Hedges said, “is admired by the far right because it has turned its back on humanitarian law and uses indiscriminate lethal force to ‘cleanse’ its society of those condemned as human contaminants”.'
01817
Darren Dahly @statsepi.bsky.social · 03/10/2026
Sadly predictable. bsky.app/profile/stat...
010
Darren Dahly @statsepi.bsky.social · 03/10/2026
Yep. bsky.app/profile/walk...
050
Reposted by Darren Dahly
Richard Van Noorden @richvn.bsky.social · 02/10/2026
Scientists have repeatedly warned that flawed studies are affecting the results of systematic reviews in medicine and other fields, but it’s rare to find such a clear example, says @floriannaudet.bsky.social . Read more here: www.nature.com/articles/d41...
nature.com
Prozac use for childhood depression skewed by single flawed medical trial
One small study in Iran swayed meta-analyses in favour of antidepressant use in children, researchers say.
1183
Reposted by Darren Dahly
JsonGeller @jgeller1phd.bsky.social · 02/10/2026
New tutorial finally in press with @rmkubinec.bsky.social @chelseaparlett.bsky.social and @matti.vuorre.com. It has everything you could possible want: Quippy headings, a whole lot of beta, bayesian analyses and frequentist analyses side by side in harmony. link.springer.com/article/10.3...
rdcu.be
27825
Darren Dahly @statsepi.bsky.social · 03/10/2026
Plus we *already* had that problem before AI. I've seen estimates that the "normal" exponential growth of academic papers is 7-10% annually.
040
Reposted by Darren Dahly
Hetan Shah @hetanshah.bsky.social · 03/10/2026
Good piece from @jburnmurdoch.ft.com & @sarahoconnorft.ft.com on AI in science. It’s making some bits faster, but there is a new ‘verification tax’ taking up time. And there are heightened bottlenecks in physical experiments & data collection. AI is a workflow problem www.ft.com/content/4508...
ft.com
The AI Shift: Is AI supercharging science?
Productivity gains in analysis are getting stuck in physical-world bottlenecks
56522
Darren Dahly @statsepi.bsky.social · 02/10/2026
👊
1111
Reposted by Darren Dahly
In Preparation @inprep.bsky.social · 29/09/2026
inpreparation.substack.com
Sixth Grant Resubmission Described As Most Faithful Adaptation Of The Odyssey
CHAPEL HILL, NC—Praising it as the definitive treatment of the source material, literary scholars confirmed Monday that Prof.
02710
Darren Dahly @statsepi.bsky.social · 02/10/2026
bsky.app/profile/stat...
000
Darren Dahly @statsepi.bsky.social · 02/10/2026
www.irishtimes.com/opinion/2026... 🎯
irishtimes.com
Fintan O'Toole: Living in Milwaukee with a Mayo granny automatically makes you Irish. Living here doesn’t
We have twice as many new citizens coming through the channel that demands no actual connection to Ireland
000
Reposted by Darren Dahly
Cole Donovan @colesci.bsky.social · 29/09/2026
Not enough people take seriously "funding delays"/"bureaucratic nonsense can kill people" but here it is right here. If I was mad when a patient died because it took a few extra months for lawyers to try to look for a legal basis for an international data transfer, I'm incandescent, now.
cnbc.com
NIH funding cuts delayed a promising childhood brain cancer trial. Patients lost time they didn't have
A delayed clinical trial underscores the stakes of federal research funding cuts for children with DIPG, a deadly brain tumor with few treatment options.
317684
Reposted by Darren Dahly
arXiv @arxiv.bsky.social · 01/10/2026
arXiv has updated our policy on rate limiting for all submitters. This update was made to fairly distribute moderator time & support the arXiv community of staff, volunteers, readers & authors. Please read our announcement to learn more: blog.arxiv.org/2026/10/01/updated-r…
216573
Reposted by Darren Dahly
Melissa Sharp-Crowe, MPH, PhD² @sharpmelk.bsky.social · 02/10/2026
The living evidence approach is increasingly used, particularly for intervention questions. However, maintaining and consistently reporting these reviews remains challenging, as fewer than half were updated over two years.
jclinepi.com
Living Evidence Syntheses in Practice: Methodology, Standards, dissemination and publication challenges.Paper 1: Introduction - Are Living Evidence Syntheses Truly ‘Living’?
This first paper in the Living Evidence Synthesis in Practice series examines how living evidence syntheses (LES) have been defined, implemented, reported, and updated over time. It introduces key con...
001
Darren Dahly @statsepi.bsky.social · 02/10/2026
I'll take things Cork city council can't seem to get a grip on for 500 Alex. It's wet and falls from the sky. What is rain? Correct!
140
Darren Dahly @statsepi.bsky.social · 02/10/2026
Zero value created. Zero social benefit. Pure transfer of wealth, preying on the vulnerable. I don't understand how anyone involved sleeps at night.
1193
Reposted by Darren Dahly
NPR @npr.org · 02/10/2026
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
n.pr
He was banned by betting sites, and filed for bankruptcy. Then he relapsed on Kalshi
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.
1321182
Darren Dahly @statsepi.bsky.social · 02/10/2026
Pouring one out for people doggedly trying to publish research that evaluated a now badly outdated LLM.
2160
Reposted by Darren Dahly
Hilda Bastian @hildabast.bsky.social · 02/10/2026
When we started the Cochrane Collaboration—over 30 years ago!—I wrote a proposal for consumer participation in the organization & its work, including setting up a Consumer Network as one of the constituent groups... 1/2
173
Reposted by Darren Dahly
Klaus Pforr @klauspforr.eurosky.social · 02/10/2026
The sheer figure of 20% blows my mind. Experts are probably well aware of that. That seems to be a little higher than the chances for russian soldiers to die within one year on the front. And we talk about scaring them away by depriving them of money or putting them in camps. And people think it's
12013
Darren Dahly @statsepi.bsky.social · 02/10/2026
QS or die trying.
110
Darren Dahly @statsepi.bsky.social · 01/10/2026
static.klipy.com
Boo This Man Meme
ALT: Boo This Man Meme
130
Darren Dahly @statsepi.bsky.social · 01/10/2026
*shhhhh*
010
Darren Dahly @statsepi.bsky.social · 01/10/2026
Why not.
020
Darren Dahly @statsepi.bsky.social · 01/10/2026
cc @ronancarbery.bsky.social
000
Darren Dahly @statsepi.bsky.social · 01/10/2026
bsky.app/profile/stat...
0123
Darren Dahly @statsepi.bsky.social · 01/10/2026
As many as you want.
140
Darren Dahly @statsepi.bsky.social · 01/10/2026
Free t-tests at the Starbucks in Dublin. First come first serve.
7322
Reposted by Darren Dahly
maura quint @mauraquint.bsky.social · 01/10/2026
Yes every woman has been harassed, many assaulted. But every woman has also experienced invisible loss from moments she avoided harassment. She felt a space becoming unsafe, so she left, while men stayed on. And in leaving, she lost: opportunities, experiences, learning, promotions, even simply fun.
168186644685
Reposted by Darren Dahly
Jim MacMillan (he/him) @jimmacmillan.com · 01/10/2026
And this conversation could almost be a CMAT song: expressing genuine sympathy for Ed Sheeran while absolutely taking him apart.
youtu.be
CMAT On Embodying Funeral Humor in “Euro-Country” | The Daily Show
YouTube video by The Daily Show
001
Reposted by Darren Dahly
Barbara Fantechi @barbarafantechi.bsky.social · 01/10/2026
An ERC committee member said in front of a crowd that there was already a triage of applications based on the applicant's CV. Now he expected that AI would be used. Preparing an ERC takes MONTHS, you have to work out the financial plan as well as the science. Imagine being doomed from the start.
63712
Reposted by Darren Dahly
Richard Shaw @richardshaw.bsky.social · 01/10/2026
"The population and systems medicine board awarded just three grants in spring 2026, which represents a success rate of 3.7 per cent, compared with an average of 12.7 per cent in 2025 and 18.6 per cent in 2024."
151
Darren Dahly @statsepi.bsky.social · 01/10/2026
static.klipy.com
Roll Safe: Feel Me, Think About It Meme
ALT: Roll Safe: Feel Me, Think About It Meme
020
Darren Dahly @statsepi.bsky.social · 01/10/2026
Sadly he did not tell the guy right next to me who is reading this to NOT EAT HIS STINKY FUCKING SANDWHICH THREE INCHES FROM ANOTHER HUMAN FACE.
350
Darren Dahly @statsepi.bsky.social · 01/10/2026
Praise be to the aircoach driver who told everyone to listen to their devices using headphones.
1180
Darren Dahly @statsepi.bsky.social · 01/10/2026
lol ok then
090
Darren Dahly @statsepi.bsky.social · 01/10/2026
A need for reproducibility is another factor. I need a recipe someone else can replicate.
150