Help me think of an engaging physical way to demonstrate the problem of selection on statistical significance. My best idea right now is to take a Galton board and drill holes in the bottom so some of the balls with |z| < 2 fall out.

Like 500 social scientists just got a Nature publication today. This will eventually be a DID for someone.

Say I wanted ~9k USD to buy out the teaching time of a prof (a brilliant coauthor of mine) so he can work on creating a validated ground truth dataset for a challenging data extraction and labelling task that current public LLMs (e.g. GPT5) have not yet saturated. Who do I pitch?

Snacking cakes by Yossy Arefi is the most dangerous cookbook. It’s entirely 1 bowl cakes that you can make in under 1 hour, like this chocolate sesame one. Perfect for when you need to eat cake at 9pm on a Sunday.

Such a happy example of people practicing evidence-backed living: www.nytimes.com/2025/10/20/w...

Quarto friends! I need your help: We are implementing a new QMD parser in Quarto. It will be super nice. But it's a big change, and we want to minimize the impact. 1. Can you share a link to your Quarto project at github.com/quarto-dev/q... 2. repost this and let your Quarto friends know too?

I think this is kind of neat and I don't think anyone else has noticed it (I've looked and I can't find anyone who has) osf.io/preprints/so... Maybe I should back off "justification" language, but it's at least a remarkable coincidence. I still think someone else *must* have noticed it...

Great news on @malengo.org: With a new large investment from The Shapiro Foundation (theshapirofoundation.org), we'll be able to bring several hundred vocational training and university students from Kenya, Uganda, and Rwanda to Europe over the coming years! More here: malengo.org/malengo-secu...

I'll be in SF (well, Mountain View) February 16ish to 22ish. Who should I meet? What should I be doing? My time is booked Feb 20-22, but I'll have time before. Relatedly, anyone want me to talk on statistical power or using LLMs to code ~all political science articles?

No Kings (Canadians that miss Queen Elizabeth)

A very much non-exhaustive list of talks that I enjoyed at MAER-Net. 1. Nikolay Kudrin's JMP on detecting and measuring p-hacking (in a way more disciplined way!). We're moving past "I dunno looks good in simulation." I need to spend time with this paper. drive.google.com/file/d/1UmuE...

I love that Gelman’s lecture is no slides and chalk

All the cool kids are saying deconvolution these days

I thought this was quite a nice (and appropriately pessimistic) discussion of our paper on power in political science. All that I would add is that we found a small minority of research topics with high power! podcasts.apple.com/ca/podcast/i...

I can’t believe I’m now considering having 2 protein shakes some days. wtf

Apparently she said she was thankful for kaya toast but the teachers didn’t know what that was so they just wrote toast. Singapore wins again.

I love doing row row row your boat with my toddler but her form is just terrible

Not surprising! Camel, eye of a needle, etc

Canadian students are so polite they say thank you when they turn in their tests.

Love this place

I'm giving a midterm exam right now and while this mode of assessment is LLM-resistant, it's really not great. I feel bad that this cohort of students is going to face a lot a more stressful tests.

Toronto people: don't forget to get your mooncakes streetsoftoronto.com/food/celebra...

If anyone has advice on submitting to APSR via the Registered Report track, I'd appreciate a DM. docs.google.com/document/u/0...

If you don’t yet exercise, strongly consider starting regular indoor rowing. It’s not fun, but: 1. It’s a full body workout, muscle and cardio 2. It can be done in about 20 min/day 3. It’s not so hard to fit a C2 erg in many homes 4. It’s low impact and your chance of injury is low

It’s nice to see the CEO is at least aware of and seemingly opposed to the culture problems on here. Gives me hope.

My kid just asked me what number is the most likely to come up if he rolls two dice and I’ve never been more ready for something in my life.

Can anyone tell me what “social science foo” is? Some kind of workshop? Anyone have experience? DM or reply 🙏

Shana tova 🍎 🍯

I’m really excited about this project. We’re carefully using and validating LLMs to code many features of academic articles. We’re going to scan basically all of political science, and at APSA we’re going to show preliminary results in 6 top journals.

Come see our work on using LLMs to track political science research methods at APSA at 4pm today! We find the latest LLMs beat graduate student RAs at extracting information from academic papers

Is Your Model Hot or Not? Come find out at the Reliable Political Science panel with open science/metascience papers by @jjvincent.bsky.social @ryancbriggs.net @jjhfahey.bsky.social and others. @yusakuhoriuchi.bsky.social and I are discussing. Saturday 4 pm East Meeting Rm. #17 #apsa2025

LLMs aren't bad at categorizing things, you're bad at describing your categories

As late as 1986 infants in the US underwent surgery without anesthetic bc doctors thought they couldn't feel pain. They received only muscle relaxants (to stop them from moving). The past is a strange & horrifying place, & future people will probably feel similarly. www.newsweek.com/when-doctors...

This is a paper I really care about. I feel the core message is very important for social scientists in general, and political scientists in particular. "Quantitative Research in Political Science is Greatly Underpowered." (with A+ co-authors)

The pretty draft is now online. Link to paper (free): www.journals.uchicago.edu/doi/epdf/10.... Our replication package starts from the raw data and we put real work into making it readable & setting it up so people could poke at it, so please do explore it: dataverse.harvard.edu/dataset.xhtm...

Darkly funny how a strong emphasis on unbiasedness via the credibility revolution plausibly ended up making the published literature more biased.

Wild how economists and political scientists worry so much about unbiased tests **in their papers** and yet basically ignore how their journals filter on significance. Given our noisy tests, the latter creates huge bias away from zero.

Eggnog is just a kind of flip, which is a nice thing to realize because then you can riff on it very easily. This is an “Estonian eggnog,” where I added Vana Tallin to the base. 👌

Hearing your toddler joyfully attempt to say spaghetti is a top 5 human experience. How is the TFR not higher?!

Going to EA events is weird

This is wild. Kudos to Sophie for her tenacity.

okay team! what software/programs are we using for research lab management? Trello? Basecamp? Asana? Looking to manage multiple projects w/ many RAs and lots of ongoing tasks better than my tiny brain can do on its own

Tried the wild blackberry simple syrup in blackberry metropolitans (split base brandy and benedictine, orange bitters). It has such a beautiful colour

Making Japanese curry for the first time and I had no idea you could make and then store a roux. Amazing.

If the average power of a test in a discipline is ~20% and 1% of published results are nulls, then there is almost no plausible way to work out the math so you don’t see absolutely *enormous* amounts of selection on significance. Sig results are always over like 100x favoured

Oh hey I crossed 3 million metres rowed

I get why it works like this, but no inline code in your quarto YAML makes me sad

It's very human to only double check that a process is working when you get a weird result. It's also very bad practice, because sometimes your "right" result is due to a bad process and you will be misled. Social scientists (economists) do this kind of asymmetric checking. arxiv.org/pdf/2508.20069

Okay that’s enough tradwife content for a while