Fabio E. Tonti

Bsky is already a pocket full of experts in any topic. And, no, I don't mean the people who are experts in *any* topic if it's trending, I mean the ones who post long and fascinating threads about minor or major specialist details.

I was thinking with a friend about how to describe the harms of AI, especially in a teaching and labor context, and came up with calling it a “coordinated campaign of mass deskilling” and I feel like that succinctly describes a lot of the problem.

I'm glad, I lol'ed in the right places then :D

This one and the late night show one got me to seriously lol. Turns out that following people on bsky for long is still no guarantee for identifying sarcasm.

Changes in pediatric cancer survival rates since 1975:

Leukemia: 45% -> 85%
Lymphoma: 73% -> 94%
CNS (brain/spine): 59% -> 75%

I have no patience for these brand-building professional contrarians who absolutely know they are lying about the state of lab leak evidence at this point.

I like your post, but maybe he didn't mean it just as literally? (anyway, p3 of your thread is prolly the most important part)

We are an #rstats lab now.

Still a #julialang dev, but we are officially exiting the Python-first mindset after a year of trying to make it work for our lab.

Does anyone know how it compares to his older "observation & experiment"?

Well, I'm actually from Carinthia, but I've lived in Vienna for nearly two decades. So kinda yes?!

An Introduction to the Theory of Observational Studies Provides an introduction to the theory of causal inference when randomized experimentation is unethical or infeasible

Paul Rosenbaum is such a prolific author with clear style (and sometimes an interesting way of repeating some central points). I'm really looking forward to his new book "An Introduction to the Theory of Observational Studies" (with R examples!! ).

link.springer.com/book/10.1007...

Ha. But while pretending to be the opposite they don't really mean it!

Haha. No 😅

Ding Peng's notes (arxiv, not sure if made into a book) on linear models! A real gem.

Won't be trusting an LLM with my tax return any time soon... (from: openai.com/index/introd...)

My current fave on here is someone writing a lot of thoughtful things about the state of a field, only to eventually dismiss stats as a "bunch of arbitrary rules".

What are those "stats" you're talking about? (tbf they specify it a bit)

New rule:
If you’re going to rant about something, you have to say what you think the thing is doing and what you think its proponents claim.

Because I keep reading rants that reveal the problem is the ranter’s understanding.

#dataviz 📊 The Man Who Loved Pies.

An afficianato of pies, Émile-Justin Menier (1826-1881) published an album of the French economy nearly entirely using area proportional sector pie charts after the 1875 Paris Exposition (by Emile Cheysson)

bit.ly/3DDdTB4
1/2

These things still shock me, not just the trickle down effects, but how people can have careers without knowing or having read what they cite.

Inside the Collapse of the F.D.A.

Phenomenal take on what's (terrifyingly) happening to FDA, by @jeneeninterlandi.bsky.social @nytimes.com (gift link below). Excellent historical context + overview of how and why we've gotten to the current moment. Looking forward to teaching from this resource.
www.nytimes.com/2025/07/08/m...

hey every single journalist who still uses twitter as your primary site, does the fact that the chatbot is promoting the Final Solution rise to the level of a news story or no

stop making this the global hub for news communication

Chris Rufo, a journalist
Crémieux, an academic

do words even mean things anymore? linguists in shambles

There's a lot of calling Crémieux an academic and Chris Rufo a journalist going on in this news story accusing a man of misrepresenting his identity

Darum dürfen Gemeindebau-Mieter keine Klimaanlage haben | Heute.at Klimaanlagen-Verbot: Volksanwältin Gaby Schwarz kritisiert Wiener Wohnen. Gemeindebauten werden zur Hitzefalle, fordert Einzelfallprüfungen.

Recht auf Split-Klimaanlage jetzt!

www.heute.at/s/darum-duer...

Klingt mittel- und langfristig super! Kurzfristig bin ich in Wien jedenfalls für ein Recht auf Split-Klimaanlage.

Book review: "A First Course in Causal Inference" by Peng Ding. muse.jhu.edu/article/963649

Sorry for this : I wouldn't call anyone "ignoring variance" a frequentist!

Used my "all good fun until someone loses an i" joke about complicated subscripts again

Cultural inception, they have an agenda 😂

FOUNDATIONS OF THEORETICAL STATISTICS. 313 It should be noted that there is no falsehood in interpreting any set of independent measurements as a random sample from an infinite population ; foi any such set of numbers are a random sample from the totality of numbers produced by the same matrix of causal conditions : the hypothetical population which we are studying is an aspect of the totality of the effects of these conditions, of whatever nature they may be. The postulate of randomness thus resolves itself into the question, “ Of what population is this a random sample ? ” which must frequently be asked by every practical statistician.

Curious to know what people take from this passage. (It's not a trap! 😜)

I'm not even sure what I take from it. I just think that users of stats might be alarmed by the question "Of what population is this a random sample?”

cc @stephensenn.bsky.social

royalsocietypublishing.org/doi/pdf/10.1...

all i want is to one day own a modest sized home in a walkable neighborhood and raise money for shelter animals. wear an outfit i like, walk to the grocery store, buy some nectarines, feed cats, and live in peace. just don't understand why achieving this is so hard