God bless this phenomenon
God bless this phenomenon
6 (phew!) on Wordleβthat's how I know I'm not sleeping well.
I've found that asking students "how would Mr Beast design a randomised trial to evaluate X" can elicit some much more creative responses than "how would *you* design it?"
I asked a class of students if they'd ever watched Tipping Point and they looked at me blankly. Scratch that example.
I liked them better than Pulp's "Something Changed".
These lyrics were one of the readings at my wedding.
It's clearly AI-canonical that a Researchfish lives *out* of water.
Should we put together a "sorry you're leaving" card or something? (I asked AI for help)
help.researchfish.com/en_US/resear...
The dinosaur lake still looks like a crime scene.
"Stone Penge" is looking resplendent.
Crystal Palace Park will look amazing when its refurbishment is finished.
Almost nobody in the office today, naturally, but they still managed to steal most of the milk I'd tried to stash in the fridge [waves fist like an angry old man]. Happy Friday everyone
15th century keyboard cat www.smithsonianmag.com/smart-news/a...
Yes, I am back at work, I promise.
And obviously, if a faithful is banished they take their money with them; if a traitor is banished their money is shared between remaining players; if there are only faithfuls left at the end they keep their money; if any traitors are left they steal the faithfulsβ money.
You neednβt reveal your beneficiaryβs name, and can change it anytime, but people know (for some reason) if youβve seen the βsolicitorβ about changing your will.
Idea for TV show: Traitors x Inheritance x Marple:
Each player keeps the money they personally win in tasks, and has a βwillβ naming another current player as their sole beneficiary if theyβre murdered.
Illustrated London News...illustration, of the NYE 1853 Iguanodon dinner, with added Xmas hat and tree
Wishing all our friends, followers, and well-wishers a peaceful and relaxing few days ahead x
Happy Friday everyone
A very clever, prolific statistician who I look up to recently said to me "I think all statisticians work in the potential outcomes framework, don't they?" I'm not so sure. arxiv.org/abs/2301.11976
Things have already changed, and that machine is so mercurial. What *would* have happened has already vanished, a seductive phantom, completely unobservable.
The best bit about the show Tipping Point is when the host, Ben Shephard, says "let's find out what would have happened if you'd decided to play". There's always a nagging doubt at the back of my mind: that's not really what *would* have happened, is it?
The journal's revenge: "Before we can further process it you are kindly requested to make the following corrections to meet the journal's requirements (please also refer to the Submission Guidelines)"
link ππ€
Personalised Decision-Making without Counterfactuals (Dawid, Senn) This article is a response to recent proposals by Pearl and others for a new approach to personalised treatment decisions, in contrast to the traditional one based on statistical decision theory. We argue that this approac
Yes, four candles... (HT @thameschoral.bsky.social and @simonywaking.bsky.social)
Once you see it you cannot unsee it.
You know how as a reviewer/editor you dislike that rush of end-of-year manuscripts that are slipped under the wire, before the Christmas shut-down, but without a hope anyone will action them until January? Well, I just did it myself. The lure of getting that manuscript off my desk was too strong...
They understood principles of good data analysis in Gertrude Stein's day, if not good data governance.
Software companies who add annoying, random pop-ups to their products asking if I would recommend them to a colleague will, ironically, never know how much greater their customer satisfaction would be if only they stopped doing that..
π’ As one of the next round of TRMP PhD students (below) you could join me, Clare Robinson, @averoniki.bsky.social and @marionkcampbell.bsky.social to work on developing a typology of research outputs in trials methodology, based at @wiphcem.bsky.social. Details here: www.findaphd.com/phds/project...