Pablo Geraldo Bastías

Great work by @pablogerbas.bsky.social! Loved the clear, causal lens on educational mobility — such a productive framework. The insights on Chile’s 2015 tuition-free policy were especially compelling. Thanks @mebucca.bsky.social @andreacanales.bsky.social @taniahutt.bsky.social for the workshop!

`tinyplot` v0.4.2 is now available on CRAN + R-universe 🎉 Mostly bug fixes, but includes some important integration improvements for Positron IDE users. Release notes: grantmcdermott.com/tinyplot/NEW...

#rstats

Which Kind of Science Reform What hope is there for science reform, if we can't agree on what to reform? Right now, principles are more important than practices.

How can we reform science? I have some ideas. But I am not sure you’ll like them, because they don’t promise much. elevanth.org/blog/2025/07...

I am often told that public critique of published articles must also solve the issues found. I think this frequently enforced requirement hinders scientific self-correction.

Blog post:

mmmdata.io/posts/2025/0...

🔥Coming July 2: 'Metrics and Models'!🔥

A new seminar series on advanced modelling w/ impact across health/society.

🌍 Open to *ALL*!
🕑 Weds 2pm UK alternating weeks (online)
🔗 metrics-and-models.github.io
📬 metrics_and_models-subscribe@maillist.ox.ac.uk

Brilliant speakers. *Please share*!

There's no doubt that editors for academic publishing need more help and support to keep things going.

But my god, this isn't it.

I've published in a number of OUP outlets. This would force me to reconsider. I suspect other #SkyStorians will, too.

Should LLMs be used to review papers? AAAI is piloting LLM-generated reviews this year. I wrote a blog post arguing that using LLMs as reviewers can have bad downstream consequences for science by centralizing judgments about what constitutes good research.

bryanwilder.github.io/files/llmrev...

🚨 REPLICATION REPORT UPDATE: One year ago, a tweet by John Holbein alerted me, @ollefolke.bsky.social, and @jopieboy.bsky.social to a paper with a shocking result about Sweden’s law criminalizing the purchase of sex.🧵

Folks, always share your code. It doesn’t have to be perfect to be helpful. And if you feel that it’s still too messy or not sufficiently clean to be shared, you shouldn’t submit yet. After all, there could be mistakes in your mess.

Also, *please* don’t compare this to the climate change (denial) discourse. I’m strongly opposed against such rhetorical moves that try to cash in on the hard-earned trust that *other* scientific fields have built up.

Update: the application deadline for this position has been extended until Feb. 12!

GEORGE LUCAS IN 1999: a trade embargo is going to spark the galactic reckoning and collapse

ME IN 2025: ah, okay

We are delighted to announce a call for papers for a forthcoming special issue on ESR @europeansocreview.bsky.social

Education and Social Mobility: Celebrating Richard Breen’s Contribution to Sociology

Deadline for submission: 15 of June 2025

More details on the call 👇

SFI is a research hub, home to between 20 and 50 resident and visiting researchers at any given time. SFI is currently seeking applications for full-time resident faculty. These 5+year appointments offer broad intellectual freedom and encouragement to take risks.
1/2

We’re thrilled to announce that this year’s keynote speaker is Prof. Aaron Clauset, from CU Boulder. He is one of the world's foremost experts in Network Science and Complex Systems

Apply by 3 March
www.maths.ox.ac.uk/events/summe...

@aaronclauset.bsky.social
@colorado.edu

Ask Cantor 😅

NEXT CALL: Tenure Track Assistant Professor position in Demography and Population Health (REF. POL-TTPT-2025-01) NEXT CALL: Tenure Track Assistant Professor position in Demography and Population Health (REF. POL-TTPT-2025-01) 12.12.2024 RRSS WhatsApp RRSS Facebook RRSS Twitter RRSS email Copiar URL The...

We are hiring!! (2 positions) TT Assistant Professor position in #Demography and Population Health. DEADLINE 02/02/25 Please share
www.upf.edu/web/politiqu... #sociology

New working paper out today with @epiellie.bsky.social called "Do LLMs Act as Repositories of Causal Knowledge?"

Can LLMs (ie ChatGPT) build for us the causal models we need to identify an effect? There are reasons to expect they could. But can they? Well, not really, no.

arxiv.org/html/2412.10...

Announcing the ISA RC28 2025 Summer Meeting at UCLA!
Conference theme: “Social Inequality and Labor Market Restructuring;” Keynotes by Michael Hout and Xi Song

Conference dates: August 4-7, 2025
Abstracts due: February 17, 2025

See you in L.A.!

`etwfe` v0.5.0 is now available on CRAN (and R-universe). grantmcdermott.com/etwfe/

As a reminder, `etwfe` makes it easy to estimate Extended TwoWay Fixed Effects a la @jmwooldridge.bsky.social. Super flexible and good for nonlinear models, recovering heterogeneous TEs, etc.

#econsky #rstats

1/3

How to Interpret Statistical Models Using marginaleffects for R and Python by Vincent Arel-Bundock, Noah Greifer, Andrew Heiss <p>The parameters of a statistical model can sometimes be difficult to interpret substantively, especially when that model includes nonlinear components, interactions, or transformations. Analysts who...

Imagine finding out @vincentab.bsky.social @noahgreifer.bsky.social and @andrew.heiss.phd wrote a thing and it's open access 👀

Awesome paper about {marginaleffects} R/python packages in JOSS (which needs to join Bsky)

www.jstatsoft.org/article/view...

🚨 We're hiring! 🚨

Join us as an Associate Professor in Social Demography, in association with @stjohnsox.bsky.social.

We're open to a range of specialisations: family, fertility, gender, migration, population health, inequalities & more 🌍

Apply now ➡️ www.sociology.ox.ac.uk/article/asso...

Contamination Bias in Linear Regressions -- out today in the AER!

www.dropbox.com/scl/fi/x4bc1...

Excited to present my ongoing book project at Nuffield college on Wednesday. Very grateful to @cmonden.bsky.social for the invitation. Hope to see some friendly faces if anyone is in Oxford this week www.nuffield.ox.ac.uk/news-events/...

And @guilhermeduarte.bsky.social's causal inference one too

go.bsky.app/FdemGAZ

I'm trying to compete with @stephenjwild.bsky.social's DAG People starter pack, because economists believe in competition Open to suggestions! go.bsky.app/Fa2XSDH

Illustration of a computational workflow for cultural evolution that connects abstract theory to real-world data. The arrows indicate logical and computational dependencies among theoretical, statistical, and scientific elements of a project. For example, an effective inferential model depends upon generative models, a question about those models (estimand), and the structure of the available evidence (sample).

Theorist bridge trolls barking at you to formally connect theory to data? Wondering how, without troll magic? We can help! "Bridging theory and data: A computational workflow for cultural evolution" With @dominikdeffner.bsky.social @natyfedorova.bsky.social Jeff Andrews. www.pnas.org/doi/10.1073/...

Like, I just asked Claude to check some of my code, and

1) it assumed a variable has range (1,2) instead of (0,1) just because, and changed my original code without warning

2) it omitted like 6 variables, again without reason and without warning

Using LLMs for code review is amazing and terrifying.

Amazing because in a few seconds you get good suggestions for improvement.

Terrifying because it makes unexplainable changes based on random assumptions about the data.

Book Review: Eric Turkheimer's "Understanding the Nature-Nurture Debate" Or, some thoughts on The Gloomy Prospect and the Gloomy Present

I wrote about Eric Turkheimer's recent book on "the nature-nurture debate", which should be of interest to people thinking not just about the genetics of behavior but complex traits more broadly. A 🧵: