Tamkinat Rauf

Summers conferred with Epstein frequently about how to extract sexual favors from a Harvard econ grad (AB '04, PhD '09)

The grad is from China

Epstein and Summers referred to her by the codename "Peril"

Racism and sexual exploitation in one efficient package

bit.ly/3LHpin8

Appreciated this point: “there’s the ethically or methodologically corrupt core and then the larger group of influencers who promote things when they should know better...”

Social media could be much more useful if folks didn’t promote articles they haven’t yet taken the time to carefully read.

Good advice!

More evidence of Matthew effect within siblings.

I'm facilitating a causal inference reading group next semester for Sociology PhD students. (I will also be learning!) If there are (1) pedagogical articles or (2) empirical examples in soc that you ❤️, will you share in the comments? [And please RT to help me crowd-source!]

Opinion | A.I. Is on Its Way to Something Even More Remarkable Than Intelligence

Interesting essay. I struggle to understand how we can jump from something advanced autocomplete to feeling emotions. But that is not far from how sociologists already think about the socialization in humans.

Robustness is better assessed with a few thoughtful models than with billions of regressions | PNAS Robustness is better assessed with a few thoughtful models than with billions of regressions

Great piece on the absurdity of brute force multiverse analyses.

www.pnas.org/doi/10.1073/...

“Multiverse analyses require thorough, theory-based model selection. Otherwise, they become a ‘dangerous tool’ that drowns valid models in misspecified ones, needlessly eroding trust in science.”

A plea for thoughtful models by @kauspurg.bsky.social

#MetaSci

36 Hours in Madison, Wis. Embrace this beer-and-cheese-loving Midwestern capital with farmers’ markets, cozy supper clubs and picturesque lakeside strolls.

Happy to see Madison featured in NYT!

Although Madison is an objectively beautiful place, it is really the prosocial and friendly culture of this city that make it so special.

If you have more than 36 hours, visit the state parks nearby. WI camping (esp in autumn) is a surreal experience.

Inequality Readers. Generally, My Best Guess IBE, in y.

At the blog, I wrote about two very interesting recent methods articles - Inference to the Best Explanation and External/Construct Validity.

Very thoughtful pushback against the ascendancy of the credibility revolution.

asocial.substack.com/p/inequality...

Hope you enjoy!

Findings are entirely selection

A big flaw with this recent “AI increases research success” study. The study did NOT directly compare researchers who used vs didn’t use AI. What they found is people who used words like “significant” & “groundbreaking“ more had bigger success. Maybe they just had success bc results were better?

I would love to see if findings replicate once you remove keywords that obviously indicate that the researchers had some statistically significant and theoretically important findings.

Might there be a chance that the researchers show are publishing in high-impact journals (which is the indicator of "quality" here) after Chat-GPT release are actually finding more "significant" results for unrelated reasons? (e.g., luck, better research ideas)

This is the list of words that is used to identify Chat-GPT use in this paper. Among this list are the words: "significant", "profound", "groundbreaking", and "revolution[ary?]".

In academia, the pinnacle of achievement is a pdf no one can access and I think that's beautiful

New jobs for computational social scientists at UNC and USC: unc.peopleadmin.com/postings/307... amd uscjobs.sc.edu/postings/194...

Why do some ideas spread widely, while others fail to catch on?

Our new review paper on the PSYCHOLOGY OF VIRALITY is now out in @cp-trendscognsci.bsky.social (it was led by @steverathje.bsky.social)

Read the full paper here: www.cell.com/trends/cogni...

Is ‘Joyspan’ the Key to Aging Well?

Will Joy-Adjusted Life Years (JALYs) become widely adopted health-outcome measures? *

* I seem to recall @davidmcutler.bsky.social years ago making reference to jogging-adjusted life years, so the JALY acronym may already be claimed.

www.nytimes.com/2025/07/18/w...

Why Do Liberals Drink Lattes?1 | American Journal of Sociology: Vol 120, No 5 Popular accounts of “lifestyle politics” and “culture wars” suggest that political and ideological divisions extend also to leisure activities, consumption, aesthetic taste, and personal morality. Dra...

The authors could have learned a thing or two from sociology! www.journals.uchicago.edu/doi/10.1086/...

Cultivate a couple of hobbies. Ideally, things that have nothing to do with your day job and that bring you joy, even if you're not great at them.

How prediction error drives memory updating: role of locus coeruleus–hippocampal interactions The brain constantly generates predictions based on one’s knowledge of the world, as captured in memory. When these predictions are in error, our knowledge base must be revised to remain relevant. Her...

How prediction error drives memory updating: role of locus coeruleus–hippocampal interactions: Trends in Neurosciences www.cell.com/trends/neuro...

There may be a trade-off between the cognitive resources we need to process large amounts of data and carefully examining data. By the same logic, feedback from 1-2 careful readers may be more useful than from several readers who lack the skills or willingness to appropriately engage with your work.

But can we reduce noise in the data we do have? I think yes, and much less advice exists out there about how to do that. I think we can reduce noise through thoughtful, unemotional reflection about the data that we already have. It means, not necessarily reading more, but reading carefully.

How to get more data? Read more. Write & submit more. And get tons of feedback from others before submitting. We've all heard this advice.

Ideally, we want to adjust the brain's model so it reflects reality as closely as possible. To do that, we need to improve the model by either giving our brain more data or less noisy data.

Interpretations should vary case-by-case. But, in practice, I've noticed that same people tend to have the same interpretations regardless of the specifics of the case (which makes sense, given the Bayesian brain!). This fallacy is especially common among grad students w/ less publishing experience.

Interpretation 1: This is a terrible paper. Reaction: Radical rewrite.
Interpretation 2: Bad luck. Reaction: Do nothing.
Interpretation 3: Paper is OK, but there's room to improve. Reaction: Some rewriting.

How does this apply to publishing? Take the example of journal rejections. I think there are 3 ways in which we broadly interpret and thus react:

To summarize the key idea: our brain is a Bayesian machine trying to iterate the best-fitting model of the world. Sometimes we over-interpret random correlations. Other times we desensitize ourselves to the environment and miss important causal info.