Sometimes I wonder if we have all been using the same set.seed() value this whole time

The blue book has arrived. Big thanks to @robcalver.bsky.social

Join our Many-Analysts Simulation Study—yes, you read that correctly—accepted as Stage 1 Registered Report in (AMPPS) @psychscience.bsky.social. We're trying to find out how researchers' simulation design choices shape methodological conclusions. Further info: osf.io/8vcxh/files/...

Now that the semester is over, I want to share the most powerful question you can ask when learning statistics. It will sometimes send you down a rabbit hole, but it will also show whether people understand what they are saying. When you read or hear "X assumes Y," ask yourself: why, and for what?

At the Moulin Rouge, The Dance, by Henri de Toulouse-Lautrec, 1890

Norm Matloff (1948-2026) @matloff.bsky.social I was made aware of the post below made by his daughter. We lost another friend and valued long-time contributor the #Rstats community, gone far too soon, and sure to be missed. His memory will be a blessing.

Reasons to be a believer:

Rob Calver@robcalver.bsky.social · 4w ago

Happy to announce that the winner of a shiny new copy of Bayesian Workflow is @felipefv.bsky.social. I can assure you this was a totally random draw and genuinely had nothing to do with his comment on the original post! Congratulations, Felipe! 😀

🎉 This is finally out on @natcomms.nature.com @natureportfolio.nature.com! Ever wondered what happens to your #brain when you become an expert at something? 🧠 If the answer is “yes” (+bonus points if you like #chess), check out our latest #fMRI work below! www.nature.com/articles/s41...

Andrea Costantino@costantinoai.bsky.social · 9mo ago

Super excited to share a new preprint! We asked a simple-but-big question: What changes in the brain when someone becomes an expert? Using chess ♟️ + fMRI 🧠 + representational geometry & dimensionality 📈, we ask: 1️⃣ WHAT information is encoded? 2️⃣ HOW is it structured? 3️⃣ WHERE is it expressed? 1/n

Interaction effects are very common in psychological research, but they are typically hard to replicate. A suspected reason for this is measurement error. Because of the poor replicability, a common recommendation is to not model interactions. 🧵

Note to self: subscribe to incidents on GitHub to avoid wasting one hour of your life

I am giving away a free copy of the #BayesianWorkflow book by @statmodeling.bsky.social, @avehtari.bsky.social, @rmcelreath.bsky.social et al!! Please like, repost, and follow to enter. I will randomly draw the winner next Weds July 8. 😀 routledge.com/9780367490140 #RStats #DataScience #Bayesian

Finally had the time to revisit @djnavarro.net's blog post about MASS and try stuff on my own. Across Linux/macOS/Windows on CI, I got the same difference. The (unexpected imo) thing: macOS and Windows had the same LAPACK version and still disagreed, which I guess means the issue is further down...

I am quite excited to attend this: crsuzh.pages.uzh.ch/msmr/program/ I will try to go over some misconceptions (in my understanding) that I have seen out there in the literature since the infamous day when I decided to ask, "How can I make this simulation reproducible?"

Something I saw recently: apparently, people will write and publish a paper showing that results obtained with a certain R package seem weird. Maybe, just maybe, a better solution for literally everyone is to reach out to the package author before publishing it?

"I have proved depression" That was my reaction as a first-year bachelor student once with SPSS

Mattan S. Ben-Shachar@mattansb.msbstats.info · 2mo ago

Psychologists doing exploratory factor analysis be like: #statsmeme

🚨I have this preprint, on causal inf in SEM, for psych science. I did submit to AMPPS, and they wanted applied examples (that’s their thing). while these methods work, the HARD step is ensuring the application meets the assumptions, so didn’t want to force examples. Anyone have ideas for a journal?

A small 🧵 about frustrations and opportunities w/ open-source research software for the social sciences: Came across a new paper in a top methods journal, explaining/demo'ing a new R package. Sounded v. cool, so was excited to dig in. What I found was largely a mess...

🚨 @rmcelreath.bsky.social @statmodeling.bsky.social & @avehtari.bsky.social are coming on the show mid-June to discuss their new book, Bayesian Workflow! ONE listener gets to bring a real Bayesian problem onto the recording and have the three of them work through it live. Here's how to enter 🧵

Part of the issue is the world doesn’t owe you an answer just because you have an interesting question, and I suspect many of our interesting social science questions will go unanswered for a very long time.

Anyone here interested in pseudorandom numbers/simulations (focused in R) and copulas? I have an idea for a package, but maybe it doesn't make sense at all. So a chat would be nice 😅

Anyone here interested in pseudorandom numbers/simulations (focused in R) and copulas? I have an idea for a package, but maybe it doesn't make sense at all. So a chat would be nice 😅

That completely unnecessary diversion from your work, but I finally decided to figure out why I was getting these bowties/butterflies. Most of that is needed for the shape, but it was the only way to explain why the center is darker

We don’t need to drink water every day (Rohrer, 2026)

Julia M. Rohrer@dingdingpeng.the100.ci · 3mo ago

Today I learned about yet another number that is essentially made up 🥲 pubmed.ncbi.nlm.nih.gov/12376390/

PLEASE SHARE: Serious request for a future scientific collaboration. Do I know any historians/sociologists who works with, or love working with historic ego documents. Diaries, letters, notes, etc. Especially those that describe real, or wished for, romantic partners/interests? email me, DM me!

If you're interested in #reproducibility, and/or a fan of Vonnegut's Cat's Cradle, check out this Veritasium video. A process is reproducible (good), then not (bad), then reproducible with a different result (very bad)

The disaster I never imagined having to worry about

YouTube video by Veritasium

youtube.com

Question for the more experienced folks: if a reviewer signs the revision document, does that mean one should feel free to reach out for further clarification about a specific point/request?

Question for the more experienced folks: if a reviewer signs the revision document, does that mean one should feel free to reach out for further clarification about a specific point/request?

The intellectual freedom: being smart enough to know how dumb you are and can be. Plus, always keep learning and being humble about it #bless #feynman

Felipe Fontana Vieira@felipefv.bsky.social · 3mo ago

I learned this last week, and it sucks (persistent identifiers). My current solution is exactly GH + Zenodo, as it has a built-in integration, so you can more easily archive and create a DOI for GH repositories

Let us not forget also: GitHub is owned by Microsoft

Darren Dahly@statsepi.bsky.social · 9mo ago

Perhaps we are at the point where universities should be making themselves much less dependent on microsoft.

As a PhD student, what upsets me about researchers not sharing (even a small part of) their code is that many are people I trust as competent. I'm not asking to find a mistake; I'm asking because I literally think I can learn from it. Yet 4 out of 4 ghosted so far.