Cameron Patrick
@cameronpat.bsky.social
biostatistician @ University of Melbourne Statistical Consulting Centre. enjoyer of multiple imputation, RCTs, and DAGs. always graph your data. also runs, bikes, hikes, etc. he/him #BiInSci 🏳️🌈 https://cameronpatrick.com/
Surely someone has done a quantum mechanical riff on this copypasta. "The missile knows where it is because it doesn't know how fast it's going"
Ryan Moulton@moultano.bsky.social · 4h agoIt's hard to believe the original text of this is from a real training manual. What did they think they were saying? knowyourmeme.com/memes/the-mi...
gotta say I really don't love it, but am also not shocked, when a far-right politician turns to conspiracy theories about "globalist bureaucrats" www.abc.net.au/news/2026-08...
somebody needs to fix "Newcastle University" and "University of Newcastle" being different institutions in different countries on opposite sides of the world. perhaps the vice chancellors could have a sword fight to the death, and the losing uni has to change their name or something
“‘Out of curiosity,’ says the patient, hoping to delay the injection, ‘what was the odds ratio for those without the genetic variant?’ The doctor pauses, puts down the needle, and turns back to the study. ‘The odds ratio for those without the genetic variant was also 4.’”
Noah Greifer@noahgreifer.bsky.social · 16h agoKnowing that I said something profound enough to be in your blog post is an honor :) My own irreverent take on odds ratios: ngreifer.github.io/blog/an-odds...
My take on p-values: 1. p-values do what they are designed to do, which is not what most people using them imagine them to do. 2. Trying to fix p-values is a trap, because no single-number summary can do what people want p-values to do! 3. Trying to explain p-values is also a trap, because...
Julia M. Rohrer@dingdingpeng.the100.ci · yesterday“A p-value is the most widespread statistical concept that is not definable in a single sentence“ CHECKMATE
also creating potential financial incentives for individual study doctors to maybe alter data seems pretty dangerous!
Jonathan Cohn @jonathancohn.bsky.social · 16h agoThese betting markets sites are so socially corrosive. www.theguardian.com/commentisfre...
This is the way.
"Online Rent-a-Sage" Bret Devereaux@bretdevereaux.bsky.social · 16h agoI think the best thing about federalism is that I don't actually have to care very much about a senate primary in another state. I hope Michiganders get someone they like, I don't need to have an opinion! Meanwhile, here in NC, @roycoopernc.bsky.social looks to be in a very strong position.
the correct response to an unknown number call is an orbital ion canon strike
Nick (derogatory) ✨@slothropsmap.bsky.social · 16h agoConsider the people you know in 2026 who are wiling to answer an unknown number, listen to a pitch, and then willingly subject themselves to several minutes of questions about politics, a topic which almost no one alive enjoys - and ask yourself how well these folks represent the rest of us.
oh lol I discovered that I'm supposed to be doing a 3 Minute Thesis thingy next week (requirement for my postgrad enrolment that I had completely forgotten about) and they want a catchy title and a slide by end of today. oooops
This exactly. In fully-automated luxury gay space communism, you will be able to *choose* between making spreadsheets with your artist commune polycule and being down bad in your castle.
@lastpositivist.bsky.social · yesterdayI think this is too clever by half - enjoy making the spreadsheet for who's doing the dishes in your artist commune polycule with 7 guys defined by one personality trait, meanwhile I'll be crying into my luxurious poster bed while living in a castle.
Every “labor shortage” is really a “ability to pay the market clearing price for labor” shortage.
this afternoon has been a lot of scrolling while MCMC model fitting goes brrrr. I regret to inform everyone that nothing interesting occurred in this time
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...
The medical world has sat in an uncomfortable tension of recognizing that RCTs bring often great quality data, and so wanting to use them as cohort studies, and recognizing that RCT enrollment almost never looks like the average real patient, making them garbage cohort studies
John Mullahy@johnmullahy.bsky.social · 2d agoPrediction: This paper will generate a lot of discussion. www.nber.org/papers/w35544
whoever named the "NARFCS" method was entirely blissfully unaware of how Australians would inevitably pronounce it, or entirely too aware in the latter case, NARFCS given
okay, stats/econ people: is "instrumental variable estimator" or "instrumental variables estimator" the preferred term? (my supervisor prefers the former, but the latter seems more common in academic literature?)
Man goes to see the Cyclops. Says he's depressed. He wants to get back to his wife and home, but he keeps running into fatal predicaments along the way. Cyclops says, "Prognosis is simple. Nobody can help you." Man starts crying. Says, "But Cyclops, I *am* Nobody"
Hello I have made this due to a mutual having issues with some folks on here forgetting this fact and shouting at him for it. Feel free to use it as a handy PSA x
I don't think people are ready for this kind of joke yet.
oh lol the version of Acrobat Reader on my Mac is somehow old enough that the "Check for updates" page 404's and now it complains whenever I open it. gg Adobe
yes sickos: "Across April, May and June, nearly one in every two vehicles sold was either electric or hybrid [...] fully electric vehicles outperformed hybrid model EVs for the first time, despite hybrids recording their second-highest share on record." www.abc.net.au/news/2026-08...
Australia records biggest-ever surge in EV sales
Nearly one in every two new vehicles sold was either electric or hybrid across April, May and June.
abc.net.au
And here it is with spaces for text so you can use it as a meme template:
John Harper@johnharper.bsky.social · 5mo agoHere it is with the proposed re-ordering of the frames.
💯 this. I miss shows where episodes were actually episodes, with a self-contained and largely predictable "bad guy of the week" or whatever arc and incremental progress towards an overarching season plot (but not too much, and if you missed an episode or two it usually didn't matter)
mtsw@mtsw.bsky.social · 3d agoI'd also add that the rhythm of pre-streaming TV - where the content would feature rising action that wouldnt resolve but instead go into an act break cliffhanger - was also highly addictive. bsky.app/profile/camp...