Per Engzell

Assistant/Associate Professor in Sociology at University of Cambridge An opportunity for an academic position as a Assistant/Associate Professor in Sociology is available, as advertised on jobs.ac.uk. Apply now and explore other academic job openings.

Exciting news, join us in Cambridge as Caius & Homerton are hiring for yet another Assistant/Associate Prof in Sociology🎉

www.jobs.ac.uk/job/DQS875/a...

What happens if the explanatory and response variables are sorted independently before regression? Suppose we have data set $(X_i,Y_i)$ with $n$ points. We want to perform a linear regression, but first we sort the $X_i$ values and the $Y_i$ values independently of each other, forming data set $...

For those who haven't yet seen this classic: stats.stackexchange.com/q/185507/2126 (someone whose manager was insisting that they do this ...)

This is population data so taking percentiles shouldn’t be that hard

Honestly even more concerned that there’s a ~0 correlation throughout 80% of the distribution

Your guess is as good as mine

"That's the news from Lake Wobegon, where all the women are strong, all the men are good-looking, and all the children are above average."

All major typewriters can be used to either commit academic fraud or facilitate junk science, a test of 13 models has found.

Wage returns to human capital resulting from an extra year of primary school: Evidence from Egypt In this paper, we examine the wage returns to an extra year of primary school using a policy reform in Egypt, which reduced compulsory primary schooli…

Policy reforms to *reduce* educational attainment were detrimental for disadvantaged boys, in Egypt. www.sciencedirect.com/science/arti...

Is College Really “the” Equalizer? New Evidence Addressing Unobserved Selection Article: Is College Really “the” Equalizer? New Evidence Addressing Unobserved Selection | Sociological Science | Posted March 3, 2026

New paper out in @sociologicalsci.bsky.social!

We revisit the college-as-equalizer debate with heckman-style selection models and find little evidence in favor of college being an equalizer!

@zhenghaowen.bsky.social @professorholm.bsky.social

#sociology

sociologicalscience.com/articles-v13...

Damn. Another journal jumped the shark, it looks like.

Welp, the BBC got to me. Fill me in on what I need to know about loneliness in the last decade or so

I heard there was a secret code
That purged effects of survey mode
But you don’t really care for bias, do ya

Picture of Felix on flyer advertising his seminar entitled "Random placement but real bias"

We're delighted to have Prof Felix Weinhardt giving the @cepeo-ucl.bsky.social seminar this Thursday!

He'll discuss biases introduced when randomising across schools/regions and what we can do about them!

🕕3-4pm Thur 5th Mar
📍Online or in-person (219, 26 Bedford Way)

Sign up: tinyurl.com/yanfx8j7

Yup, though this was pre llm. I was tempted not to answer just because I didn’t want to do their work for them

Had a similar experience where all the data was already on osf. I wonder how many authors just don’t bother to answer (or email bounces bc job moves, spam filters etc) and are classified as nonreplicable despite the data being out there

Stop anthropomorphizing ants. They're totally fed up with it. They had a meeting. "Eek! People keep anthropomorphizing us! What do we do?" "Derek, what did I tell you? We've got an agenda to work to here. Please raise your point as an AOB." "OK, sorry Judith." "Right, volunteers for the tombola"

Can’t go wrong with a good alliteration

Abstract text of working paper

What do we know - and what should we know - about economic inequality and social mobility in preindustrial societies? This new WP by our Affiliated Scholar @guidoalfani.bsky.social identifies the main gaps that need to be filled in reconstructions of wealth & income distributions.
bit.ly/4l26cWx

💯

Honestly I'm even more intrigued the more I'm learning about it

No shade at all on your paper I just find it a fun fact about Finnish conscription... obviously someone thought it important enough to include!

I wonder how many people claimed they always dreamed of becoming one just to get out of conscription

PS: Claude Code doesn't work in secure computing environments (for now - my only remaining competitive edge)

Loool. We need more people like you on grant panels!

Willing to consider anything that could give me a competitive edge at this point

Do I know anyone who's attempted to max out the word count for the title of a grant? How did it go?

Appreciate the honesty... cute titles are like marmite, like or hate. I'm not the biggest fan, but agree these may be too dry

The paper that taught me 'masculinity' used to be considered a social skill in 1980/90s Finland

Björn Borg, dominant force in tennis during the 1970s and early 1980s

Boston, England, United Kingdom is 0 hours ahead of City of London, England, United Kingdom 16:00 Monday, Boston, England, United Kingdom BsT UTC+0 is 16:00 Monday, City of London, England, United Kingdom Bst UTC+0

Thanks but not the Boston I had in mind...