iiinova — where your digital self keeps evolving

Darren Dahly @statsepi.bsky.social · 06/10/2026

"Can I please get a proper extract from the actual database?" "Sure, here you go..." #FML

Darren Dahly @statsepi.bsky.social · 28/09/2026

Who could have guessed that the editors/reviewers of "Evidenced based complimentary and alternative medicine" might be pretty bad at the evidence-based part. 😆

3214

Darren Dahly @statsepi.bsky.social · 23/09/2026

Why do people keep trying to make me use this? Do they hate me? www.trustpilot.com/review/read.ai

260

Darren Dahly @statsepi.bsky.social · 23/09/2026

I enjoyed this. Was gonna rant, but even I'm sick of hearing it. www.nature.com/articles/s41...

164

Darren Dahly @statsepi.bsky.social · 22/09/2026

This was everything I needed to know about Mubi to cancel my free trial.

110

Darren Dahly @statsepi.bsky.social · 18/09/2026

Thoughts and prayers please for this poor auld soul.

5609

Darren Dahly @statsepi.bsky.social · 17/09/2026

I got excited because I thought you said Munster :)

110

Darren Dahly @statsepi.bsky.social · 17/09/2026

You have to admit, the face validity of this scale is pretty strong lol. theleahfiles.substack.com/p/the-most-c...

010

Darren Dahly @statsepi.bsky.social · 16/09/2026

Sounds really interesting @desfitzgerald.bsky.social. Against Automation: Resisting AI Futures in Teaching and Research. Nov 20. cc @olivia.science Register here: www.eventbrite.com/e/against-au...

084

Darren Dahly @statsepi.bsky.social · 16/09/2026

Thank you genius with the PhD who selected every level of education. Of course you were allowed to do this by the survey designer, so....

5130

Darren Dahly @statsepi.bsky.social · 15/09/2026

WHOA there champ! We are just talking about possible associations here buddy. Settle down about causes, lol. We so aren't there yet.

2202

Darren Dahly @statsepi.bsky.social · 15/09/2026

Ok I'm getting mad now for real for real.

8402

Darren Dahly @statsepi.bsky.social · 15/09/2026

Attention to detail is very important in this thing of ours.

2270

Darren Dahly @statsepi.bsky.social · 14/09/2026

I think about this passage almost weekly. What exactly I think about it, I'm not entirely certain. 😜

2101

Darren Dahly @statsepi.bsky.social · 12/09/2026

I don't think there is a sample size reported in this entire paper.

150

Darren Dahly @statsepi.bsky.social · 12/09/2026

Look, you do not want me taking this class lol.

160

Darren Dahly @statsepi.bsky.social · 10/09/2026

Medical statisticians can relate:

2304

Darren Dahly @statsepi.bsky.social · 03/09/2026

What's stopping you? :) These are patient obvervations and modelling with continuous time.

020

Darren Dahly @statsepi.bsky.social · 02/09/2026

Good to know our new boss thinks that applied medical/biostatistics and research data management are pretty important priorities for facilitating high quality research in our region. cc @bapalmer.bsky.social

160

Darren Dahly @statsepi.bsky.social · 01/09/2026

For when Y = mX + b just won't do.

4131

Darren Dahly @statsepi.bsky.social · 28/08/2026

At least they've stopped even pretending.

5180

Darren Dahly @statsepi.bsky.social · 26/08/2026

Excellent. Bravo to @hardyschwamm.bsky.social & colleagues for getting this through. All research outputs @uccresearch.bsky.social must be made open access w/o embargo (with v. limited exceptions) www.ucc.ie/en/research/... libguides.ucc.ie/oa-policy-su...

UCC Open Access and Research Outputs Policy

These FAQs accompany the UCC Open Access and Research Outputs Policy. Read the Policy and supporting information at the Open Research pages. For any queries, contact the Library at:

openaccess@ucc.ie
What the Policy requires

Authors must make their research outputs openly available immediately at publication via Green, Diamond, or Gold Open Access. For publications, this means depositing the Author Accepted Manuscript (AAM) or the Version of Record (VoR) via Pure (which feeds the Cork Open Research Archive, CORA) at the date of publication, without an embargo, unless an approved exception applies (see Section 4 of the Policy).

140

Darren Dahly @statsepi.bsky.social · 24/08/2026

Quite a lot of discordance between the observations and conclusion here. I have to stop reading this stuff now for my own sanity.

060

Darren Dahly @statsepi.bsky.social · 23/08/2026

Gonna tell my kids this was Cofnas trying to not say the n word.

0223

Darren Dahly @statsepi.bsky.social · 11/08/2026

ok this was probably too ambitious.

5300

Darren Dahly @statsepi.bsky.social · 07/08/2026

I am a golden god. All hail stackoverflow. stackoverflow.com/questions/44...

0130

Darren Dahly @statsepi.bsky.social · 07/08/2026

20 minutes later. Somehow, even better.

360

Darren Dahly @statsepi.bsky.social · 07/08/2026

Not what I was looking for - but damn, I kinda like it.

4280

Darren Dahly @statsepi.bsky.social · 03/08/2026

And many of those same people don't think enough imo about this closely related point. statsepi.substack.com/p/a-conversa...

“Excellent. Next, we must also consider that our goal is to get as many patients as we can onto improved treatments as soon as possible. So if the early trials strongly suggest substantial average benefit in some group of patients, it might be ethically dubious to continue withholding that treatment for other patients that might also benefit. At this point, it becomes a matter of clinical judgment rather than scientific investigation. The crux of the problem is that one could always imagine some special type of patient for whom the treatment works differently. The possibilities are endless. But at some point a decision to make this medicine more widely available must be made. And once that decision is made, they lose the ability to continue testing the treatment effects of the new drug in randomized controlled trials because that would require withholding the treatment from some patients who might be reasonably likely to benefit.”

141

Darren Dahly @statsepi.bsky.social · 03/08/2026

IMO too many people misunderstand this: Paraphrasing @stephensenn.bsky.social, many RCTs should be designed to answer *Can* this Work? In this case, enrolling "unusual" patients can be very useful indeed. statsepi.substack.com/p/some-point...

We must carefully consider which patients to enroll on our RCT. This will largely depend on the overall goals of the trial. In the initial phase 3 trials for a new treatment, we are often most interested in seeing if the intervention can work in a “best-case” scenario. This means that we select patients in a manner that maximizes the internal validity of the trial, with little or no consideration for the external validity or generalizability. In turn, this means recruiting patients that are most likely to benefit from, and adhere to, the proposed treatment (based on our current understanding). It also means recruiting a more homogeneous sample to reduce natural variability in the outcome. This will make it easier to see the effects of the intervention, if there is one, using a smaller sample than would be required to see the same effect in a broader, more varied sample. This best-case scenario makes sense for newly tested treatments, since it costs less money and exposes fewer patients to as of yet unknown risks, and because if we fail to see an effect under these optimal conditions, it’s probably safe to conclude that we can move on from this intervention to pursue other ideas.

172

Darren Dahly @statsepi.bsky.social · 22/07/2026

About to give a giga-lecture on the ideas underpinning both frequentist and Bayesian approaches to statistics to a room full of clinical academic fellows. Wish me luck friends.

4380

Darren Dahly @statsepi.bsky.social · 14/07/2026

🤩 bingkaiwang.github.io/RCT_Bench-ma...

36519