iiinova — where your digital self keeps evolving

Reposted by Rodrigo Lassance

Carl T. Bergstrom @carlbergstrom.com · 11/09/2026

"...solving problems is only a tool and proxy for achieving the primary goal of conceptual understanding and insight. Forgetting this in the world of AI may turn the tool against the primary goal."

231788

Reposted by Rodrigo Lassance

Laerte @laertecoutinho.bsky.social · 15/07/2026

Tira de 2017 - saiu na Folha @folha.com

Tira em 4 quadrinhos.
1) Mulher, sozinha, olha para algum ponto. Texto: “Certas coisas eu percebo olhando.”
2) Mesma mulher, com uma prancheta, fazendo anotações. Texto: “Certas coisas eu percebo tabulando.”
3) Vazio. Texto: “Certas coisas eu percebo”
4) Mulher, frente a uma pia, lavando louça. Toca o queixo. Texto: “muito tempo depois.”

8971334

Reposted by Rodrigo Lassance

okay Kelly @kmdoublev.bsky.social · 14/04/2026

"if you know what I mean": innuendo "iff you know what I mean": dogwhistle

26715

Reposted by Rodrigo Lassance

Paintings by Jim Mastrian @jjm4.bsky.social · 11/03/2026

Iceland landscape painted for a friend. Not my favorite subject matter - too much green. This was a tough acrylic painting. Onto the next painting. 2026 #acrylic #acrylicpainting #artist #artists #art #painting #originalart #traditionalart #Portland #Maine #iceland #cliff #mountain #waterfall

1262345

Rodrigo Lassance @rflassance.bsky.social · 28/01/2026

If you're (1) using a parametric model and (2) interested in testing hypothesis of practical equivalence (e.g., testing something like |mu| < 0.001 instead of mu = 0), you can use this to test whatever you like without having to correct alpha: www.tqmp.org/RegularArtic...

tqmp.org

110

Reposted by Rodrigo Lassance

Stephanie Wang @sweiwang.bsky.social · 10/01/2026

the meeting of the Society for Inexact Philosophy will be held some time in 2026 at an university

67014

Reposted by Rodrigo Lassance

Dominique Baker @bakerdphd.bsky.social · 28/08/2025

Some people asked for it so here you go!

Screenshot of my syllabus which reads: Valuing Diversity. The diversity students bring to this class is a valuable resource because varied backgrounds and opinions enhance discussion. Research suggests that learning is improved by exposure to diversity in the classroom. It is Dr. Baker’s intent to present materials and activities that utilize and are respectful of diversity of all kinds. This class is a place where everyone is free to learn, to express doubt, and to assert convictions. However, with freedom of speech comes responsibility and
accountability for that speech. To that end, students are asked to pay attention to both the effect and the intentions of their words, and to avoid deliberately using language that is demeaning to others. When listening to other students, assess both the intent and the effect of those words before assuming an offensive motive. Use language that corresponds to how people name themselves and their identities. If students are concerned with the tenor of discussion in class, they are more than welcome to meet with Dr. Baker privately to discuss their concerns. Dr. Baker welcomes and appreciates students’ suggestions about how to improve the value of diversity in this course.

1011212

Rodrigo Lassance @rflassance.bsky.social · 09/07/2025

Just updated the arXiv version of our upcoming paper 🚀 We show how to build three-way tests (accept, reject, or stay undecided) using confidence/credible regions. They’re logically coherent and control type I & II errors—even when testing multiple hypotheses. No significance corrections needed!

000

Rodrigo Lassance @rflassance.bsky.social · 12/06/2025

While I love the em-dash, I hate the fact that — contrary to the grammar of my mother language — in english we are supposed to used it without spaces, which feels objectively worse to me 🥲

010

Reposted by Rodrigo Lassance

Zeta Of 1 @zetaof1.bsky.social · 07/05/2025

A friend of mine, I recently found out, does really fantastic memes about economics and econometrics. The initial ones are in Russian, but I convinced her to translate them into english so I could share them with a broader audience, I think many of you will appreciate them!

I've played with Monte-Carlo Method... Got lost in the game

3268

Reposted by Rodrigo Lassance

Tiago Peixoto @tiago.skewed.de · 12/03/2025

🚨 New paper on ArXiv: “Uncertainty quantification and posterior sampling for network reconstruction” TL;DR; We present an efficient method to sample the entire ensemble of possible network reconstructions that are compatible with an indirect observation, e.g. a dynamics. Short thread: 1/N

1016553

Reposted by Rodrigo Lassance

Will Lowe @conjugateprior.org · 13/12/2024

It is the time of christmas parties, so here is your seasonal guide to never having heard of Slavoj Žižek. medium.com/the-hairpin/...

medium.com

The Best Time I Pretended I Hadn’t Heard of Slavoj Žižek

One weird trick to frustrate the hell out of a Marxist bro

0163

Rodrigo Lassance @rflassance.bsky.social · 09/12/2024

3) We introduce a simple testing procedure based on the posterior probability of the hypothesis that can be seamlessly combined with MCMC. Aside from having some neat properties, it can also be easily transformed into a Bayes factor.

Print of the definition of the pragmatic region oriented test, i.e. PROTEST.

110

Rodrigo Lassance @rflassance.bsky.social · 09/12/2024

2) We provide multiple suggestions to help determine what a researcher means by "good enough" even when this notion is harder to ellicit. One can use priors, measurement errors, related studies and more to identify a viable threshold.

110

Rodrigo Lassance @rflassance.bsky.social · 09/12/2024

1) We propose a method for building nonparametric hypotheses that consider researcher's opinions. For example, if the data differs from a normal by at most 1% and that is good enough for the researcher to assume normality, this can be easily inserted into the hypothesis!

Print of the definition of a nonparametric pragmatic hypothesis.

110

Rodrigo Lassance @rflassance.bsky.social · 09/12/2024

I am happy to announce that a paper of mine, Rafael B. Stern and @rafael-izbicki.bsky.social has been accepted for publication at the International Journal of Approximate Reasoning 🎉 In our paper, we show how to build and test hypotheses of practical equivalence in nonparametric settings. 🧵

Decision regions based on a significance level alpha and a threshold epsilon for the gender wage gap data presented in the paper. For higher values of alpha and lower values of epsilon, the hypothesis is rejected. For lower values of alpha and higher values of epsilon, the hypothesis is not rejected.

121

Reposted by Rodrigo Lassance

Max Berg @maxberg91.bsky.social · 20/11/2024

Men will literally prefer going Bayesian instead of going to therapy.

17216

Reposted by Rodrigo Lassance

Federico Adolfi @fedeadolfi.bsky.social · 14/11/2024

Academic writing — get utilized to it.

1134474

Reposted by Rodrigo Lassance

JASP @jaspstats.bsky.social · 29/10/2024

Hi Bluesky! ☀️ We are an open-source statistics program that is free, friendly, & flexible. Armed with an easy-to-use GUI, we enable both classical & Bayesian analyses. Over 340 universities in over 70 countries use JASP. Follow us to get notified on our latest features & stats news.

25120

Reposted by Rodrigo Lassance

Jeremy Allen @jeremy-data.bsky.social · 26/10/2024

My fav starter packs so far, a thread: stats: go.bsky.app/Ki7PjpS stats: go.bsky.app/7TBN5rX causal inference: go.bsky.app/FdemGAZ package devs: go.bsky.app/N1569Qh data peeps: go.bsky.app/8TdEfdK medical stats: go.bsky.app/ArqEz36 bioinformatics: go.bsky.app/Ha64Gmv r-ladies: go.bsky.app/Vgxwa2F

18277132

Reposted by Rodrigo Lassance

Saloni @scientificdiscovery.dev · 26/10/2024

Since my previous epi starter pack was very popular, I've made another one to help you find stats & meta-science people on Bluesky! Feel free to suggest anyone who might be missing. go.bsky.app/LqYZHBX

109142

Reposted by Rodrigo Lassance

Joe Bak-Coleman @jbakcoleman.bsky.social · 17/10/2024

I made a metascience starter pack, emphasizing accounts that often post about metascience rather than specific science reform policy advocacy. go.bsky.app/PhZ1Q4g

56634

Reposted by Rodrigo Lassance

Raphael Nishimura @rnishimura.bsky.social · 12/09/2024

Ontem saíram duas pesquisas para prefeitura de SP com resultados relativamente diferentes, principalmente para o candidato Boulos. A matéria abaixo tenta explicar essas diferenças do ponto de vista metodológico. E tem a participação dessa pessoa que vos escreve 😄

1226

Reposted by Rodrigo Lassance

Tim Dawson @ironicaccount.bsky.social · 02/09/2024

lot of negativity towards AI lately, but consider : are these tools ethical or environmentally sustainable? No. *but* do they enable great things that people want? Also no. *but* are they being made by well meaning people for good reasons? Once again, no. maybe you're not being negative *enough*

69104544471

Reposted by Rodrigo Lassance

Madhu Pai, MD, PhD @madhupai.bsky.social · 02/09/2024

Powerful cartoon that speaks to the hard realities of global health for colleagues in the Global South

13417

Reposted by Rodrigo Lassance

Guilherme Duarte @guilhermeduarte.bsky.social · 01/09/2024

A starter pack with causal inference I know. Unsure if this is the correct way of doing this, but I'm learning go.bsky.app/FdemGAZ

36427

Reposted by Rodrigo Lassance

Stephen Wild @stephenjwild.bsky.social · 01/09/2024

Created a starter pack of Bayesians. It is *very* biased by who I engage with regularly and who I know is on this site. Let me know if you want to be added to the list or know someone who should be. #stats go.bsky.app/UfgChHe

215634

Reposted by Rodrigo Lassance

lorem ipsum 🇧🇷🇺🇸 @whiskeynachos.bsky.social · 31/08/2024

This is a good article, but this remains the most important point. Elon is not challenging the decision in court, he is simply acting like he's above the law and ignoring the sovereign government of Brazil. He's not hiring legal counsel, he's posting memes in English about Xandão.

Carlos Affonso Souza, a Brazilian internet-law professor, called the order “the most extreme judicial decision out of a Brazilian court in 30 years of internet law.” Yet he added that Brazil had to take some action after Mr. Musk so publicly and explicitly flouted multiple court orders.

“It’s not up to a company to decide if a judicial decision is adequate or not,” Mr. Souza said. “The company must file a complaint in a lawsuit, not just decide to not comply.”

010736

Reposted by Rodrigo Lassance

Bluesky @bsky.app · 31/08/2024

agora este é um aplicativo brasileiro 🫡

Miranda Cosgrove's character looking at a computer screen. O personagem de Miranda Cosgrove olhando para uma tela de computador.

33518758511256

Reposted by Rodrigo Lassance

Stephen Wild @stephenjwild.bsky.social · 01/09/2024

Post a meme made by you

American chopper meme. Two men are yelling st each other.

Text

Man 1: you should report marginal effects

Man 2: I reported the coefficient values. What more do you want?

Man 1: people have a hard time interpreting those values.

Man 2: minus means less and plus means more. That's good enough!

Man 1: interpreting g effe ts on the scale of interest is natural and beneficial

612926

Rodrigo Lassance @rflassance.bsky.social · 01/09/2024

post a meme made by you This one was inspired by arxiv.org/abs/2407.02754

010

Reposted by Rodrigo Lassance

Catarina Dutilh Novaes 🟥 @cdutilhnovaes.bsky.social · 01/09/2024

Brazilians online are a force of nature 😀 Welcome, fellow Brazilians 🇧🇷 Maybe now Bluesky will finally get the party started 🥳

2181

Reposted by Rodrigo Lassance

Raphael Nishimura @rnishimura.bsky.social · 01/09/2024

Starter Pack para quem tiver interesse em métodos de pesquisa do tipo survey: go.bsky.app/3H1Pf9z

13724

Rodrigo Lassance @rflassance.bsky.social · 01/09/2024

Judge Moraes initially restricted the use of VPN as a whole, but since that is not very clever he soon changed the restriction only to using VPN for accessing Twitter. Considering how high the fine is (about 35 times the minimum wage), many might find the threat credible.

110

Rodrigo Lassance @rflassance.bsky.social · 31/08/2024

Bem vindo! Aderi não faz tanto tempo, mas tem uma galera bacana por aqui, desde gente da saída em massa de quando o Musk assumiu a pessoas que postam em ambas as redes.

110

Reposted by Rodrigo Lassance

Nath Finanças 💰 @nathfinancas.com.br · 31/08/2024

Eu tô amando não ter as bets e cassinos de publi o tempo todo na TL 🙏🏽

23896081183

Reposted by Rodrigo Lassance

Rafael Izbicki @rafael-izbicki.bsky.social · 31/08/2024

📚 Conheça nosso livro "Aprendizado de Máquina: Uma Abordagem Estatística"! Ideal para quem já tem noções de estatística e quer se aprofundar em machine learning. 💻 Baixe gratuitamente ou adquira a versão impressa! 🔗 rafaelizbicki.com/ame #MachineLearning #Estatística #DataScience #CiênciaDeDados

0199

Rodrigo Lassance @rflassance.bsky.social · 31/08/2024

The app seems to be down too, but it is still available on Play Store for now. It is only a matter of time before it is removed as well, though.

110

Reposted by Rodrigo Lassance

Randall Munroe @xkcd.com · 27/08/2024

Three Kinds of Research xkcd.com/2977

343802653

Reposted by Rodrigo Lassance

Dr. Stephanie @punkrockscience.bsky.social · 21/08/2024

Holy shit, they put the data on github.

1429