Profile avatar
doced.bsky.social
Doctor in Anaesthetics & Intensive Care Medicine | Part time academic | R enthusiast | Sci-Fi fan | Dad https://doced.github.io
462 posts 1,120 followers 159 following
Regular Contributor
Active Commenter

Confidence interval #AIslop

Why oh why must we still use “type 1” and “type 2” error nomenclature. Just call it what it is. False positive, false negative, far more descriptive. “Error of the first kind”. FML. 🤦‍♂️

What are risk factors if not associations persevering.

Finally got around to incorporating all Github feedback on my open access textbook, making around 20 minor improvements, and updating some references. 17 chapters of state of the art stats and methods education, freely available for any course you teach. lakens.github.io/statistical_...

IYKYK

All these AI tools are super tempting. But the point is to read the paper. You can’t become an expert in a domain by having AI serve you up a large volume of summaries. Much better to actually read a smaller number of papers more deeply.

Philosophical question. Is POCUS now considered an extension of physical examination, or an investigation in its own right?

Excellent list

Heck yes porchetta BBQ.

Globe Safety xkcd.com/3086

do. not. trust. ai. search. results.

We need educators like this

TANK vs TESLA "We've crushed fascism before and we'll crush it again" - ⁠WW2 veteran Ken, 98, in the tank

Yep. It's terrifying how the vast majority of people are using AI without any thought to scrutinise its outputs.

Here we go again. Updated work place details. Ballot ready. #FPR @bma.org.uk 🦀

I think a lot about what Carl Sagan said in one of his final interviews.

Remember this one. In five years, or ten, or twenty. When we're a weird, dirty, backward nation that still sets fire to stuff, and places like China and India start to ask us why.

The WhatsApp AI features are super creepy and invasive. Can we all please move to signal now?

Does anyone else look at the moon and only see a filling defect 🙃

Remember the good times when the main threat to the scientific endeavor was conditioning on a collider