Per Engzell

Of course, it would be easier - in fact stimulating - to take sermons about civilisation from experts or even strong amateurs on the subject. But no. There is a well-known pattern in LinkedIn or dating profiles. Someone who claims to "enjoy deep conversations" is vacuous. Someone who "loves exploring different cultures" is parochial. Someone who "cannot stand people who don't read" reads Deepak Chopra. Something about explicitly claiming high cultural standards is suspect. Sure enough, those who go on about "Western Civilisation" - the words are often capitalised in conservative settings - never seem all that steeped in the stuff. An entry-level interest in ancient Rome is often the extent of it. Having to take lectures from the sort of person who has a Doric column as their Twitter photo: this, as much as anything, is our reduced fate as a continent.

I’m crying
www.ft.com/content/ccbe...

What the British government is letting happen to universities is unconscionable

A perfect surname for one who studies how things change.

www.jstor.org/stable/2340499

The only thing more overfitted than my model is my personality to institutional incentives

Analytical Sociology Seminar: Per Engzell Welcome to the Analytical Social Seminar with Per Engzell from University College London. Patrons, protégés, and peers: Workplace mechanisms of intergenerational inequality. The seminar is open for th...

Join us on Thursday, 11 December, at 14:30 CET for the last Analytical Sociology Seminar of the term with @pengzell.bsky.social 🔹 Patrons, Protégés, and Peers: Workplace Mechanisms of Intergenerational Inequality 🔹 More info: liu.se/en/event/ana...

Perfect, AI now wants to sign all my emails with "Per our conversation". Looks like the singularity is coming sooner than we thought.

On the (Mis) Use of the Fixed Effects Estimator Data that span multiple units and time periods allow controlling for time-invariant heterogeneity correlated with the covariates. While researchers can do this in different ways, the fixed effects es....

"On the (Mis) Use of the Fixed Effects Estimator"

(by @dlmillimet.bsky.social and Marc F. Bellemare)

published in the Oxford Bulletin of Economics & Statistics.

onlinelibrary.wiley.com/doi/10.1111/...

Do #training subsidies improve worker outcomes? Using the German case, Christine Dauth @iabnews.bsky.social shows that training #subsidies significantly increase cumulative #employment duration and #earnings in the short run and middle run for workers, especially #women.
doi.org/10.1177/0019...

A blog post giving a more thorough take on survey experiments and the credibility revolution: cyrussamii.com?p=4168

Please, clincians with the right experience, my wife’s study, and all psych ppl please share far and wide!

I got you

Green Onions One of the greatest rhythm guitar players of all time has left us

All my guitar heroes are less-is-more kinda players and Steve Cropper was a master of that style

open.substack.com/pub/braggb/p...

Niche academic tweet:

Philosophers who look like cut stones

I'm imagining this isn't going to be a long thread.

Apple could surprise remove Liquid Glass the same way it surprise added U2 to everyone's devices and I'd be first in line to call things even.

Good job universities haven't switched their entire digital infrastructure to... oh hang on

Working on something on multiverse analysis and I'm mildly amused that Steegen et al.'s piece coining the term (2016) reports 210 analyses and states that "more typical multiverses will tend to be smaller", meanwhile Muñoz & Young (2018) are like "We ran 9 billion regressions."

Saving this one next year’s syllabus

This talk by @simine.com about what other fields can learn from the crisis in psychology is excellent. I so wish sociology was listening. If 10% of sociologists knew 50% of what she says then research in sociology would be 100% better.

Our Alex Bryson continues to shine a light on the troubling downturn in young people’s mental well-being. In the US, this trend is driven by those in the labor force, as opposed to students or others outside it.

‘A fragmented field: Construct and measure proliferation in psychology.’ (2025)

From ‘Language models accurately infer correlations between psychological items and scales from text alone.’ (2025)

From ‘Not within spitting distance: salivary immunoassays of estradiol have subpar validity for predicting cycle phase.’ (2023)

Work in progress with cycle tracking data from the app Clue

Want to make nice graphs with me, starting next year? I'm hiring for a position at the University of Witten/Herdecke.
uni-wh.softgarden.io/job/61280592...

Very excited about forthcoming @sfjournal.bsky.social with Jessie Himmelstern

academic.oup.com/sf/advance-a...

How has job insecurity changed over the past 1/2ish century?

note that this paper has no identification strategy itself

Austerity in England has restricted childbearing mainly for low-income and racially minoritised women. Important research from former SRI Research Fellow @jenchanfreau.bsky.social and @laurasochas.bsky.social.

Brand new report on UCL’s strong contribution to justice and equality research – featuring our head of department Mette Berg’s work on asylum housing in northern England, among several outstanding projects.

Nature just wrote me they're one article short

58. Oasis: www.sciencedirect.com/science/arti...

57. Echo & the Bunnymen: www.r-causal.org/chapters/04-...

New paper in press at JPSP! An adversarial collaboration focusing on a large-scale test of how strongly implicit racial attitudes predict discriminatory behavior. Pre-print here: osf.io/preprints/ps...

56. Neil Young: onlinelibrary.wiley.com/doi/full/10....

Ah this makes sense, I see it now.