Arthur
@riosarthur.bsky.social
Reposted by Arthur
Finally listened to this lecture -- highly recommended if you've ever been confused about fixed effects vs. random effects models. Love that the framing starts from group-level confounding -- here's a problem, what could be solutions (rather than: here's a model, what are its features).
This time I try to explain group-level confounding and some ways to deal with it. Lecture B04 of Statistical Rethinking 2026 - fixed effects, Mundlak machines, latent Mundlak machines, intro to social network analysis and the social relations model. Full lecture list: github.com/rmcelreath/s...
Statistical Rethinking 2026 Lecture B04 - Group-level confounding and intro to social networks
YouTube video by Richard McElreath
www.youtube.com
February 2, 2026 at 10:51 AM
Finally listened to this lecture -- highly recommended if you've ever been confused about fixed effects vs. random effects models. Love that the framing starts from group-level confounding -- here's a problem, what could be solutions (rather than: here's a model, what are its features).
Reposted by Arthur
Reposted by Arthur
Machine learning research is not serious research and therefore hallucinated references are not necessarily a big deal, agrees a prestigious group of machine learning researchers
statmodeling.stat.columbia.edu/2026/01/26/m...
statmodeling.stat.columbia.edu/2026/01/26/m...
Machine learning research is not serious research and therefore hallucinated references are not necessarily a big deal, agrees a prestigious group of machine learning researchers | Statistical Modeli...
statmodeling.stat.columbia.edu
January 27, 2026 at 1:13 AM
Machine learning research is not serious research and therefore hallucinated references are not necessarily a big deal, agrees a prestigious group of machine learning researchers
statmodeling.stat.columbia.edu/2026/01/26/m...
statmodeling.stat.columbia.edu/2026/01/26/m...
Reposted by Arthur
The ultimate establishment post. Criticizing everyone else for using "fascism" for years and when you finally use it yourself, calling everyone who doesn't "perverse".
Fuck you, The Atlantic! You normalized their message with your endless paranoid scare campaign against so-called "wokeness".
Fuck you, The Atlantic! You normalized their message with your endless paranoid scare campaign against so-called "wokeness".
"Recent events have brought Trump’s governing style into sharper focus," Jonathan Rauch argues. "'Fascist' best describes it, and reluctance to use the term has now become perverse." theatln.tc/wVq7MFaa
January 26, 2026 at 12:01 AM
The ultimate establishment post. Criticizing everyone else for using "fascism" for years and when you finally use it yourself, calling everyone who doesn't "perverse".
Fuck you, The Atlantic! You normalized their message with your endless paranoid scare campaign against so-called "wokeness".
Fuck you, The Atlantic! You normalized their message with your endless paranoid scare campaign against so-called "wokeness".
Reposted by Arthur
the nyt style section vs. der spiegel
January 24, 2026 at 11:20 PM
the nyt style section vs. der spiegel
Reposted by Arthur
wieso sagt man na mensch das ist ja ne geile quadratische funktion und nicht irreparabel !
January 21, 2026 at 12:51 PM
wieso sagt man na mensch das ist ja ne geile quadratische funktion und nicht irreparabel !
Reposted by Arthur
If you are interested in all things ✨causal inference✨, please join our multidisciplinary Causal Inference Interest Group (CIIG). We host monthly seminars featuring speakers with various academic backgrounds and research interests.
Links below.
cc @clscohorts.bsky.social @pwgtennant.bsky.social
Links below.
cc @clscohorts.bsky.social @pwgtennant.bsky.social
January 20, 2026 at 12:35 PM
If you are interested in all things ✨causal inference✨, please join our multidisciplinary Causal Inference Interest Group (CIIG). We host monthly seminars featuring speakers with various academic backgrounds and research interests.
Links below.
cc @clscohorts.bsky.social @pwgtennant.bsky.social
Links below.
cc @clscohorts.bsky.social @pwgtennant.bsky.social
Reposted by Arthur
Lecture B02 of Statistical Rethinking 2026. Multilevel model expansion: workflow, cluster and feature engineering, non-centered parameterization, dank memes. Continues next week with models of population covariance and (if there is time) group-level confounding and "Mundlak machines".
Statistical Rethinking 2026 - Lecture B02 - Multilevel Model Expansion
YouTube video by Richard McElreath
www.youtube.com
January 16, 2026 at 12:11 PM
Lecture B02 of Statistical Rethinking 2026. Multilevel model expansion: workflow, cluster and feature engineering, non-centered parameterization, dank memes. Continues next week with models of population covariance and (if there is time) group-level confounding and "Mundlak machines".
Reposted by Arthur
our data story visualizing the rabbit hole people can fall into with chatGPT is on the cover of today’s @washingtonpost.com @kevinschaul.bsky.social
December 28, 2025 at 5:51 PM
our data story visualizing the rabbit hole people can fall into with chatGPT is on the cover of today’s @washingtonpost.com @kevinschaul.bsky.social
Reposted by Arthur
o cara foi fazer uma panqueca e saiu o verso de uma carta de yu-gi-oh
December 27, 2025 at 8:31 PM
o cara foi fazer uma panqueca e saiu o verso de uma carta de yu-gi-oh
Reposted by Arthur
e a prefeitura do recife que usa a fonte de persona 3 pra emitir nota fiscal eletronica
December 21, 2025 at 2:27 PM
e a prefeitura do recife que usa a fonte de persona 3 pra emitir nota fiscal eletronica
Reposted by Arthur
42 citações a um artigo que não existe 🤡🤡🤡 leiam a thread toda
a gente tá mto ferrado
a gente tá mto ferrado
And so checked out Google Scholar. Now on my profile it doesn't appear, but somwhow on Nelli's it does and ... and ... omg, IT'S BEEN CITED 42 TIMES almost exlusively in papers about AI in education from this year alone... scholar.google.com.vn/citations?vi...
scholar.google.com.vn
December 20, 2025 at 2:53 PM
42 citações a um artigo que não existe 🤡🤡🤡 leiam a thread toda
a gente tá mto ferrado
a gente tá mto ferrado
Reposted by Arthur
A propos of nothing but the term "exposome" always is a bit of a red flag to me. I understand that it's meant to invoke a parallel to the genome, but honestly it is usually followed by confusions about causality.
![Insufficient confounder control
The authors write in the abstract that the “[e]ffects persisted after adjusting for linguistic, physical, social and sociopolitical exposomes.” This is true but also easily misunderstood: They only controlled for one exposome at a time. Hence, it is possible that the mono/multilingualism variables acted as a proxy for some of the exposomes that weren’t considered in the analysis.](https://cdn.bsky.app/img/feed_thumbnail/plain/did:plc:gz53felr7btxgmbxae5aooxi/bafkreibssiqhzc6afx57cm7tefl2d73yei54bqbd4ynzev4jmqnhep3dva@jpeg)
December 17, 2025 at 8:21 AM
A propos of nothing but the term "exposome" always is a bit of a red flag to me. I understand that it's meant to invoke a parallel to the genome, but honestly it is usually followed by confusions about causality.
Reposted by Arthur
So we've got this product that basically stops a progressive feature flag rollout if we detect a degradation.
Netflix did something very similar in this paper, and for a hackweek I re-implemented the method
IN SQL!
arxiv.org/abs/2205.14762
Netflix did something very similar in this paper, and for a hackweek I re-implemented the method
IN SQL!
arxiv.org/abs/2205.14762
Rapid Regression Detection in Software Deployments through Sequential Testing
The practice of continuous deployment has enabled companies to reduce time-to-market by increasing the rate at which software can be deployed. However, deploying more frequently bears the risk that oc...
arxiv.org
December 10, 2025 at 3:41 AM
So we've got this product that basically stops a progressive feature flag rollout if we detect a degradation.
Netflix did something very similar in this paper, and for a hackweek I re-implemented the method
IN SQL!
arxiv.org/abs/2205.14762
Netflix did something very similar in this paper, and for a hackweek I re-implemented the method
IN SQL!
arxiv.org/abs/2205.14762
Reposted by Arthur
You will be visited by 3 spirits
December 9, 2025 at 4:29 PM
You will be visited by 3 spirits
Reposted by Arthur
Does anyone want a survivorship bias shortbread
November 29, 2025 at 4:50 AM
Does anyone want a survivorship bias shortbread
Reposted by Arthur
I should probably explain this, with context.
Over several years we have caught MANY researchers playing silly buggers with artificial cutoffs designed to engineer group differences.
(No one more so than the Vitamin D weirdos. One of the least reliable and most annoying areas of health research.)
Over several years we have caught MANY researchers playing silly buggers with artificial cutoffs designed to engineer group differences.
(No one more so than the Vitamin D weirdos. One of the least reliable and most annoying areas of health research.)
November 14, 2025 at 2:23 AM
I should probably explain this, with context.
Over several years we have caught MANY researchers playing silly buggers with artificial cutoffs designed to engineer group differences.
(No one more so than the Vitamin D weirdos. One of the least reliable and most annoying areas of health research.)
Over several years we have caught MANY researchers playing silly buggers with artificial cutoffs designed to engineer group differences.
(No one more so than the Vitamin D weirdos. One of the least reliable and most annoying areas of health research.)
Reposted by Arthur
Currently in a workshop for MIT CODE. I can hear conversations of other people; "I'm at stanford", "Oh I know you from {{FAANG}}".
I'm like 👋 hi I like linear algebra and did my PhD at a meh school for statistics
I'm like 👋 hi I like linear algebra and did my PhD at a meh school for statistics
November 13, 2025 at 3:14 PM
Currently in a workshop for MIT CODE. I can hear conversations of other people; "I'm at stanford", "Oh I know you from {{FAANG}}".
I'm like 👋 hi I like linear algebra and did my PhD at a meh school for statistics
I'm like 👋 hi I like linear algebra and did my PhD at a meh school for statistics
Reposted by Arthur
It’s the correct interest, just the wrong weights!
November 10, 2025 at 7:41 PM
It’s the correct interest, just the wrong weights!
Reposted by Arthur
Noooo don’t overfit your so sexy hahah
November 9, 2025 at 5:28 AM
Noooo don’t overfit your so sexy hahah
Reposted by Arthur
This is great. I am not a fan of the oscillator example - makes it seem like a physics niche thing. But so useful for us population-thinkers. I might write up a post using a population dynamics differential equation example. If I can finish cloning myself. Yeah. www.youtube.com/watch?v=FE-h...
Why Laplace transforms are so useful
YouTube video by 3Blue1Brown
www.youtube.com
November 6, 2025 at 6:15 PM
This is great. I am not a fan of the oscillator example - makes it seem like a physics niche thing. But so useful for us population-thinkers. I might write up a post using a population dynamics differential equation example. If I can finish cloning myself. Yeah. www.youtube.com/watch?v=FE-h...
Reposted by Arthur
pra desativar:
1. clica na sua foto
2. configurações e privacidade
3. privacidade dos dados
4. dados para aprimoramento da IA generativa
1. clica na sua foto
2. configurações e privacidade
3. privacidade dos dados
4. dados para aprimoramento da IA generativa
November 3, 2025 at 5:48 PM
pra desativar:
1. clica na sua foto
2. configurações e privacidade
3. privacidade dos dados
4. dados para aprimoramento da IA generativa
1. clica na sua foto
2. configurações e privacidade
3. privacidade dos dados
4. dados para aprimoramento da IA generativa
Reposted by Arthur
TLDR; The PSF has made the decision to put our community and our shared diversity, equity, and inclusion values ahead of seeking $1.5M in new revenue. Please read and share. pyfound.blogspot.com/2025/10/NSF-...
🧵
🧵
The official home of the Python Programming Language
www.python.org
October 27, 2025 at 2:47 PM
TLDR; The PSF has made the decision to put our community and our shared diversity, equity, and inclusion values ahead of seeking $1.5M in new revenue. Please read and share. pyfound.blogspot.com/2025/10/NSF-...
🧵
🧵
Reposted by Arthur
This is some of the hardest shit I've seen in my life
August 28, 2025 at 6:42 AM
This is some of the hardest shit I've seen in my life