Imagine a world where you had more time than ideas

I completely forgot people still do that!

I'd like to see them trying this in statistical methods. "I made a new type of imputation for missing data. It works really well... but if you want to see or use it, you'll have to pay me"

We must be honest about what data we do and do not have. These are all possibilities

Are popes poisson distributed? If so I estimate there could be as many as 6 popes per km2

Both per capita and per unit area-- though I believe the standard per area illustration is that it has 2 popes per square kilometre.

What is the confidence interval on that rate please?

Do you ever come across research studies that develop or somehow validate a survey questionnaire, but don't include the actual questions? What's that about?

#mentalhealth #adolescentwellbeing #trials | Born In Bradford 📢 We're hosting two webinars to introduce the IRL Trial — the world-first study exploring the impact of reduced social media on young people. Choose the right session for you: 1️⃣ Researchers and ...

If you'd like to hear about our planned trial of social media limitations among young people ("The IRL Trial"), please feel free to sign up for one of our webinars - we have one specifically for researchers, and one for stakeholders working in policy / services, etc: www.linkedin.com/feed/update/...

Nothing strengthens your argument like deleting half of it to meet the word limit

@newsfromgoogle.bsky.social Any chance you could make table borders a bit fiddlier in Google Docs? I like a challenge

2026 A.D. All the internet is occupied by AI. All? No! … One small indomitable footnote still holds out against the bots: "Message for Clarion WE KNOW YOUR LISTINING. The station has IP detection software"

kappa_vs_agreement.R GitHub Gist: instantly share code, notes, and snippets.

Code for this plot: gist.github.com/danlewer/69e...

If two people make a yes/no decision (eg. should a student pass their viva), they'll sometimes agree even if their decisions are random. If the event is rare or very common, they'll usually agree. Cohen's kappa accounts for random agreement. 0 = random; +1/-1 = complete agreement.

These are practically oriented positions with the most important duties being supporting delivery of the trial; though after data collection is complete there will be plenty of opportunities to produce research outputs if you're interested.

We're recruiting two research assistants to help us deliver "The IRL Trial" - a world-first randomised trial of social media limitations among 12-15 year-olds, and the effect on mental health. You'd be part of the Born In Bradford family. For more info and to apply: www.jobs.nhs.uk/candidate/jo...

Are you like me - do you love changing the fonts on your #rstats plots, but tire of fiddling around with extrafonts? Just load "ragg" and use the agg device - you can set the font in par (eg. `par(family = 'Verdana')` and you have direct access to system fonts! Thank me later.

Yes 100%!!! If it's not worth writing, it's not worth reading. And your brain tends to switch off before you realise it's AI. The output is optimised to prevent thought

I guess you could set it so you are only available 1 day per year

The IRL Trial - Born in Bradford

Hi there, our trial ("The IRL Trial") is funded by @wellcometrust.bsky.social and doesn't have any industry support. There's more info about the research here - borninbradford.nhs.uk/what-we-do/s...

A quote from "Consider Phlebas" by Iain M. Banks: "Still, the underlying point held; experience as well as common sense indicated that the most reliable method of avoiding self-extinction was not to equip oneself with the means to accomplish it in the first place."

Iain M Banks on avoiding self-destruction

Or worse, you find that water is dry, and then have to conclude that despite your findings, water is actually wet.

Moderately useful but only within certain paradigm. It would be more useful if you provided conversions between paradigms such as Fahrenheit to centimetres

Pockets of real deprivation

Use a more explicit estimand? Causal Risk Ratio Professor Per Engzell?

Also "it's right that we ... "

Please tell me 8% of those data points in the forest plot are wrong

Good luck ... when you've got the large hadron collider up and running, I have 2^100 interactions I'd like to test, and am currently computing the appropriate Bonferroni correction

The hype around LLMs seems to be "yes the outputs aren't good and the costs and harms outweigh the benefits, but imagine if this or a different technology was actually useful"

Those are good words