Survey experiments' popularity in political science is getting attention. What is good and bad about them? How can one maximize their benefits and mitigate their downsides? Greg Huber and I wrote up our thoughts: Paywalled: doi.org/10.1016/bs.h... Free: m-graham.com/papers/Huber...

So I guess we are back to matching? (Although, by the references cited, the authors appear to be unaware of the connection?) arxiv.org/pdf/2511.21977

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

This is an impressive project. My reaction to what it shows though is that survey experiments have gotten out of hand in polisci. I will blog more on this, but I do not think survey experiments are emblematic of the credibility revolution. Some are already interpreting as such, which is a problem.

RIP David Malone. Diplomat extraordinaire & probing academic, David headed the UN adjacent @ipinst.bsky.social where I had my first real job. He taught me so much—how to think & write clearly, how to organize productive discussions. A towering intellect who will be missed. unu.edu/news/memoria...

Reporting the treated group mean along with DID estimates of the ATT cyrussamii.com?p=4151

New paper in first view @thejop.bsky.social w/ Burde, Middleton, and Rahnama We show the promise of a community governance strategy to sustain schools in remote Afghan communities after NGO withdrawal. www.journals.uchicago.edu/doi/abs/10.1...

What a great day: legends of innovation economics Mokyr, Aghion and Howitt win the Nobel. Joel was a PhD advisor of mine, so need a full article! Included: good & bad explanations of the Indus Rev, Aghion's charisma, influence of Jon Hughes, French fashion houses: kevinbryanecon.com/mokyraghionh...

Congrats to UZH. One can read in terms of Hirschman’s Exit/Voice/Loyalty framework: the pull of sentimentality toward MIT is weak when there is abundant work to be done on global poverty and the broader home environment is so bleak.

👀 (given the remarkable robustness of BART as a static prediction method)

Currently in FirstView: “Generalizing Trimming Bounds for Endogeneously Missing Outcome Data Using Random Forests." @cdsamii.bsky.social, Ye Wang, @jlzhou.bsky.social‬ present a partial identification approach that avoids strong assumptions. This is illustrated using a simulation and replication.

Agreed — nice round up of very well informed perspectives. I found Raleigh’s analysis especially convincing but all perspectives were thought provoking.

Back to teaching or studying economics at university this September? @voxdev.bsky.social has tons of useful resources for university economics courses - I have included some examples in this thread. 1/n

WE ARE HIRING! 2 Lecturers in Quantitative Social Science. Want a friendly interdisciplinary department in one of the world's most vibrant cities? This just might be for you. Apply by: 10 Oct www.ucl.ac.uk/work-at-ucl/...

Interesting paper on design-based uncertainty for quasi-experiments www.tandfonline.com/doi/full/10....

For your weekend read I highly recommend this article on the Tampa Bay Rays and the thankless pursuit of excellence: www.nytimes.com/2025/08/06/m...

👀

🚨Call for submissions (by Aug 1)🚨 NYU "Data Science Frontiers: Society and Politics" conference. Held at NYU’s New York campus Oct 15-17. Submit a paper or extended abstract. Full details here: nyuad.my.salesforce-sites.com/NYEvents/ape... Travel subsidies for presenters. Please forward!

Polmeth 2025 kicks off today at Emory. I’ll be presenting work on inference for group interaction experiments (eg, group training, experimental games, deliberation experiments, etc.) and coauthor Sandy Gordon will introduce our new data authentication tool, Data-NoMAD polmeth.emory.edu/index.html

🚨Call for submissions (by Aug 1)🚨 NYU "Data Science Frontiers: Society and Politics" conference. Held at NYU’s New York campus Oct 15-17. Submit a paper or extended abstract. Full details here: nyuad.my.salesforce-sites.com/NYEvents/ape... Travel subsidies for presenters. Please forward!

🚨JOB ALERT🚨 We (pdri-devlab) are hiring a research manager! Come join our team engaged in policy-relevant collaborative research (mostly migration, climate, enviormnet, big data for dev) in the great city of brotherly love. Pls share widely with your network. wd1.myworkdaysite.com/en-US/recrui...

This is a lovely post comparing algorithms to compute OLS coefficients

New paper! Regression is motivated in binary treatment settings as producing a convex, conditional-variance-weighted average of heterogeneous treatment effects, but in the continuous treatment case estimates the slope of the true DRF at a point that may not exist in the data. Do AIPW when feasible

Sinner Alcaraz about to portal into the next dimension

Coco!!!

What a battle between Sinner and Djokovic. Both playing all out.

In the most recent issue of @restatjournal.bsky.social (direct.mit.edu/rest/article...), we (Kaspar Wuthrich and @karthik-econ.bsky.social) provide guidance on how to analyze and design experiments with factorial designs (or cross-cuts). A 🧵 below:

Heckman and Fang’s oped is on point and antithetical to both the current administration and opposition narratives, so clearly conveyed that it will surely be mostly ignored: The Real Story of the “China Shock” by @heckmanequation and @HanmingF

👀

NYC, more the mayoral candidates decided to weigh in on our questions. So we've updated the Meet Your Mayor quiz! See if your matches have changed, and be sure to share this with your friends! buff.ly/h82O2uT

Need support with fieldwork prep? Still time to register for our fieldwork course at the @essexsummerschool.bsky.social

Hard to win titles without a first serve

Optimal transport to match distributions, optimal transport to solve high dimensional matching problems, optimal transport to prove CLTs…

Just watched the Zheng-Gauff highlights. Instant classic.

ACIC off to a good BADBADNOTGOOD start

From our new issue: "Peer Effects and Recidivism: Wartime Connections and Criminality among Colombian Ex-Combatants" by Mateo Vásquez-Cortés. #APSRNewIssue www.cambridge.org/core/journal...

On to American Causal Inference Conference (ACIC) tomorrow in Detroit w/ papers on inference in group interaction experiments & experimental design for robust cross-context learning. I’ll also compete in the “hot ones” “spicy wings and spicy causality takes” session 😬 sci-info.org/2025-meeting/

I love the "ex ante policy" inferential stance that @beenwrekt.bsky.social develops here. Helpful reference when dealing with people who are blind to the difference between ex post inference for explaining mechanisms vs ex ante inference for testing novel interventions: arxiv.org/pdf/2501.03457

Inspired me to read it finally, and wow. Should have been required reading.

Cool. See the original post from @johnholbein1.bsky.social Then Ramdas et al. give a strategy for safe inference on sequences of tests of indefinite duration under a martingale bound. Your intervals contract at a rate slower than root-N.

Very excited to share this new working paper, joint with @sdellavi.bsky.social, Guido Imbens, and Woojin Kim bsky.app/profile/nber...

Amazed at how fast bartMachine is. Maybe makes it worth the annoying interface to Java.

At airport, flight delayed, thought I’d pickup print copy of The Economist for old time’s sake, a break from phone. $12 for an issue! Who would pay that??

rOpenSci database on cancelled NSF grants: airtable.com/appGKlSVeXni...

If you had to recommend a linear algebra textbook to upper level undergrad or grad students that did a thorough build up to SVD, which would you suggest?

Excellent example of the publicly funded basic research -> applied pipeline, even if some are trying to spin this falsely as a usual triumph for commercial research.

After many years of working on it, it feels great to finally see my job market paper out in AJPS!

👀

link 📈🤖 Finite Population Identification and Design-Based Sensitivity Analysis (Kline, Masten) We develop an approach to sensitivity analysis that uses design distributions to calibrate sensitivity parameters in a finite population model. We use this approach to (1) give a new formal analysis of

Enjoyed this discussion of Strack’s work, including on how “overconfidence”can sustain injustice perceptions that persist despite evidence to the contrary. He’s on to an animating force in politics. podcasts.apple.com/us/podcast/g...