Alex Coppock

YES! that would be v. cool.

A clunky party of DD is the declare_model() section; if we could somehow do declare_model(daggity_spec) that would be amazing. it's just that all the details (the outcome spaces, strength of covariances) are hard to get in there simultaneously

Seems great!

!!!! will look into this, that sounds like it would solve many annoying things (like how it sometimes uses older code)

(should note that I checked the r2, it was wrong, I told the AI it was wrong, and it fixed it. So there were two rounds before I believed the sim.)

Screenshot of claude just writing a design no trouble

Writing simulations in DeclareDesign just went from "I should do that, but it's kind of a lot of work" to extremely easy

Reminder to register (no fee) for the Rebecca Morton experiments conference at NYU taking place next week. Join us: nyu.qualtrics.com/jfe/form/SV_...

Per protocol analysis strikes again!

Folks, if you randomize but then don‘t analyze some of the people who got randomized (maybe because they didn’t adhere to instructions, maybe because they dropped out), randomization will no longer do all the heavy causal inference lifting.

a cartoon of mickey mouse in a wizard outfit ALT: a cartoon of mickey mouse in a wizard outfit

me typing "claude"

IMO, I think journals should be able to decide whether they review registered reports or not. Most don't, at present.

I *do not* think journals should reject papers for *having been preregistered*; that's nuts!

*maybe* this journal mistakenly thought the author submitted a registered report (or similar).

But if the position is "papers must not be pre-registered" I'd love to hear the justification.

Thank you! am screen-shotting your predictions and will assess after results come in!!

Thank you for all the support and reposts!

We've gotten a steady stream of inquiries and submissions for this competition, but also some ANXIETY that the window will close before people have a chance to submit.

We're nowhere near that! We'll update on here when we've allocated 50% of the capacity.

Very nice, thank you for the research and for the Atlantic piece.

TIL!

Very excited to see this out at @bjpols.bsky.social! In this article, I show that contemporary political news coverage makes it challenging for readers to learn information that is helpful for democratic accountability, even for very politically engaged audiences.

A brief summary:

(you're so right, that was my *actual* fav, but it sold already....)

yessss the white glaze in the ridges!!

Am I hearing you right that when the two candidates take issue positions that people care about a lot, the test-retest is closer to like 95% but among people who don't care so much about the issue, test re-test is lower, like 75%? I'm giving numbers so you'll correct me :)

Ooh, sounds v. interesting. Can you give a teaser? I'm guessing that people make the same choice about 80% of the time, is that close?

Penelope Van Grinsven and Lilly Zuckerman curate Above Board Ceramics -- this year's show is now live and is fabulous.

www.aboveboardceramics.com

[disclosure Penny and I are married!]

highly recommend this paper. the experimental design manipulates how much subjects are monitored; when asked, yes treated subjects feel more monitored.

Do they later give different responses on possibly sensitive topics? no they don't.

screenshot of the SPCO tickets page

Rough. it doesn't have to be this way! Check out what the the Saint Paul Chamber Orchestra is up to.

www.thespco.org/concerts-tic...

How AI Impacts Skill Formation Judy Hanwen Shen∗ Alex Tamkin† February 3, 2026 Abstract AI assistance produces significant productivity gains across professional domains, particularly for novice workers. Yet how this assistance affects the development of skills required to effectively supervise AI remains unclear. Novice workers who rely heavily on AI to complete unfamiliar tasks may compromise their own skill acquisition in the process. We conduct randomized experiments to study how developers gained mastery of a new asynchronous programming library with and without the assistance of AI. We find that AI use impairs conceptual understanding, code reading, and debugging abilities, without delivering significant efficiency gains on average. Participants who fully delegated coding tasks showed some productivity improvements, but at the cost of learning the library. We identify six distinct AI interaction patterns, three of which involve cognitive engagement and preserve learning outcomes even when participants receive AI assistance. Our findings suggest that AI-enhanced productivity is not a shortcut to competence and AI assistance should be carefully adopted into workflows to preserve skill formation – particularly in safety-critical domains.

Interesting paper, especially interesting it's coming from researchers at Anthropic arxiv.org/pdf/2601.20245

Among the most vivid declines in the American people's trust -- their diminished trust in other people.

Data from @gallup.com's Social Series.

I would bet that, conditional on seeing the video,

the treatment effect among those who oppose ICE
\approx
the treatment effect among those who support ICE

It's hard to get people to watch things they disagree with, though, but that's not to say it wouldn't work if they did

Call for Proposals: Data Collection for Replication+Novel Political Science Survey Experiments Alexander Coppock and Mary McGrath January 27, 2026 We invite proposals for a survey experiment replication+novel design competition. Se- lected replication+novel design survey experiments will be conducted on large samples of American respondents, quota sampled to match U.S. Census margins and filtered for quality and attention by the survey sample provider Rep Data (repdata.com). Each proposal consists of two parts: (1) a replication study of an existing, previously published survey experiment, and (2) a novel experimental design on a topic of the authors’ choosing. The replication studies and reanalyses of the existing studies will be combined into a meta-paper to be co-authored by all authors of accepted proposals along with the princi- pal investigators (Coppock and McGrath). As a condition for acceptance, authors commit to sharing the data and producing a write-up of the findings from their novel design for submission to a scholarly journal, and public posting of a working paper pre-publication.

🎺 Call for proposals 🎺

1️⃣ replicate an existing experiment
2️⃣ run a novel experiment

on repdata.com

3️⃣ coauthor with Mary McGrath and me to meta-analyze the replications and existing studies
4️⃣ publish your study

details: alexandercoppock.com/replication_...
applications open Feb 1

please repost!

After years in academia, I’m exploring data science and research roles in industry.

I'm a quant. social scientist (PhD Yale ’24, NYU) focused on causal inference, experiments, and large-scale data.

Feel free to get in touch or share; all leads appreciated. dwstommes@gmail.com

JOIN us for this year’s Rebecca Morton conference on experimental political science at NYU! March 6-7. We have a great line up of papers and posters!

Program (scroll down) here: wp.nyu.edu/cesspolitica...

Register (no fee) here: nyu.qualtrics.com/jfe/form/SV_...

Many of us separate between "family photos", social media (e.g., FB/Insta), and political opinions (BS/Threads). Today is a good time to post on "family" social media so our Trump-voting family and friends understand how mad we are, and to puncture their information bubble.

The section is searching for new editors for @jepsjournal.bsky.social ! Please check out the call here, and circulate widely: connect.apsanet.org/s42/editor-s...

Thank you! Link fixed and page updated!