Camus clearly never had to work out what was wrong with district level outcomes at the 2007 Burkina Faso legislative elections

New blog post! Let's say you have two measures meant to capture the same confounder. They're highly correlated. Can you still proceed with your regression analysis? (I admit, the title is a bit of a spoiler) www.the100.ci/2025/10/13/i...

Has anyone had success stories (or can point me to writeups) with fine tuning frontier LLMs?

Education? Completed it, mate. Last week, I defended my PhD thesis and am now a doctor! Thank you to @robfordmancs.bsky.social and @jonmellon.bsky.social for being great supervisors for 4 years And thanks to @sarahobolt.bsky.social and Ed Fieldhouse for their interesting feedback and discussion

Rex W. Douglas PhD Applied Scientist (Remote/Austin) Looking for full time and freelance projects. Hoping for somewhere stable. I've never been more productive in my life, but mass layoffs and funding collapses have been endemic.

Help! ─ 𝗔𝗽𝗽𝗹𝗶𝗲𝗱 𝗦𝗰𝗶𝗲𝗻𝘁𝗶𝘀𝘁 open to work ─ Remote/Austin → www.rexdouglass.com With new tools, I've been cooking: ▸ Machine-vision pipelines — RIOS Intelligent Machines ▸ Information-extraction pipelines — Microsoft ▸ Interactive SMS surveys — Pantheon Insights

I remember around 1995 a woman knocked on the door, doing a survey about air fresheners. I never bought any so it didn't last long but I was quite excited that someone was asking my opinion about a product or service. At last! Finally, Gen X was being consulted!

Social scientists often bemoan falling survey response rates. A big part of the story has to be the proliferation of survey requests. I took every survey I was invited to in an 8 day period and took 27 surveys totaling 33 minutes.

I would argue this is actually about Bayesian inference

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

🚨DATA RELEASE 🚨 The BES team are pleased to announce the release of Wave 30 of the British Election Study Internet Panel. Please follow the link below, and we look forward to seeing your research! www.britishelectionstudy.com/bes-resource...

Now elsevier have been harassing me personally to pay the invoice (several thousand dollars).

Has anyone else had experience with being harassed by @elsevierconnect.bsky.social over open access payments?

The lovely people @britishelectionstudy.com released the random probaility data which means we can begin to unravel some unanswered questions about turnout in 2024. A substack to follow but a starter of social class and vote/non-vote. Which party represents the working class? None of the above.

5. Today I read a paper by @sabinaleonelli.bsky.social and Alexander Mussgnug that I think illustrates this point perfectly. philsci-archive.pitt.edu/24891/1/Phil...

Does anyone have a good reference for the theory that the polls overestimated remain in 2016 because of a lack of education weighting? I've heard this theory but not sure if anyone ever fleshed it out in writing

can anyone see a downside to the plan of ordering this desktop specifically for the narrow set of workflows where I have really high RAM requirements and using a modern Macbook pro for every thing else?

Has anyone written a paper on the ideology/partisanship of pollsters?

I’ve never really understood why they don’t force separate tokens for digits. Unlike words, the individual characters of numbers are always meaningful in a consistent way

Yes! I recommend validating LLMs against a task you're actually interested in rather than trying to guess whether these failure modes indicate that it will or won't be capable.

The one grammar rule I refuse to follow is putting a full stop within a quotation rather than after it. It just feels like misquoting the original source (it changes the meaning of the original by implying the sentence ended there).

PSA: Just trotting out the aphorism that “all models are wrong, but some are useful” doesn’t mean *your* model is among the latter…

If researchers find Cohen’s d = 8, no they didn’t. (probably.) Thoughts on the distribution of Cohen's d values in psychology and why we should think about their plausibility when reading articles.

Extreme heat during the growing season increases the number of undernourished households in the following year, measured by calories, iron, and other nutrients in rural India, from Paul Stainier, Manisha Shah, and Alan Barreca https://www.nber.org/papers/w34047

In our polarized political environment, I’m excited to share my new ASR publication: “Competence over Partisanship: Party Affiliation Does Not Affect the Selection of School District Superintendents”. journals.sagepub.com/doi/10.1177/...

Paid research assistant opportunity with the British Election Study for UK-based graduate students. Help us validate turnout in our surveys against Electoral Commission records

Another way to put this is we need the Texas Instruments of LLMs

What this also shows is that it would be trivial for Open AI to solve the cheating problem. It’s not an inevitable consequence of the technology but a business choice

One thing that is underdiscussed around AI and education is how much AI chat interfaces are setup to default to helping students cheat. It's also really easy to prompt them not to do this. Compare standard ChatGPT's answer to a custom prompt that tells the AI to make the student think critically

Journals/editors please put the "no login required" link to the reviewing portal in every reminder email. I'm forced to use Outlook and it takes 10 minutes to find your first email with the direct reviewer link.

Want to easily scrape data from news media sites? There's an R package for that! paperboy "paperboy offers writers of web scrap[ers] a clear path to publish their code & earn co-authorship on the package, while deliver[ing] news media data from many websites in a consistent format."

Social scientists should not use chat interfaces when using LLMs in their research: they are impressively inefficient, and obscure/impose important methodological decisions that require thought. THREAD🧵

I have multiple papers saying versions of "this data source is only usable if you validate it for your specific use case". So many citations are "It's fine to use this data for this unvalidated use case (Mellon 2014)."

In the end we’re scientists not poets, so I think this is fine. I’d rather get a clearer communication of a smart colleague’s ideas and findings.

Please send us your nominations for the STATISTICAL SOFTWARE AWARD of the Society for Political Methodology! Self-nominations are encouraged. There are only a few days left before the deadline, but the submission materials are light and free form. @willrhobbs.bsky.social @jonmellon.bsky.social

This norm rewards (sometimes dubious) claims of theoretical novelty, rather than encouraging us to build on each other in a cumulative way. They say: send empirical pieces to “specialty journals.” But top journals like AJPS make or break careers, so the incentives are strong (and bad, I think). 2/2

For scenarios where you have a DV that is only observed for an endogenous subset of people (e.g. wages for the employed), is the Heckman selection model still state of the art or have there been advances since then?

LLMs may sometimes act like humans because they’ve read the social science research telling them how they’re expected to act

There's so much going on here and I kind of love it. Going straight into my stakeholder analysis midterm next semester

Anyone know of an accessible dataset of Australian Federal election results from 1946 onwards? Existing comparative sources seem to have some issues, e.g. v-party doesn't always have all the parties that make up the coalition, parlgov seems to have some rounding issues.

R experts. w/o running it, what do you expect to see after running these lines of code: test <- 1:10 test[1:5][1] <- 100 test

A small bit of pushback on this mostly to avoid people feeling complacent that they obviously would have caught their student doing this

While there’s a lot of concern about parts of education that AI is breaking, it also enables types of student experiences that were previously infeasible. My student capstone group built AI bots that act as enlisted troops for them to practice counseling skills on

Related to this, I think there’s potential for AIs to give students an Oxford tutorial style grilling on their essays as both a good learning experience and a check on their understanding

The Brexit realignment amid electoral volatility: The role of party blocs in the 2024 General Election doi.org/10.1093/pa/g... Paper in Parliamentary Affairs co-authored by @nuffieldcollege.bsky.social Fellows @profjanegreen.bsky.social & Geoffrey Evans with alumnus @jonmellon.bsky.social #PoliSky

🚨NEW PUBLICATION 🚨 Though people have moved on from Brexit, they still vote in line with their Brexit preferences - with age/education still separating voters. Voters now back party blocs, which matters greatly for Labour's current appeals to Reform voters. 🧵 academic.oup.com/pa/advance-a...

I have some colleagues who are trying allowing full use of AI for homework but give most of their points for being able to explain what their code is doing without access to AI. They seem cautiously optimistic about the results

Interesting writeup of how chatgpt is sometimes intersecting harmfully with delusional behavior. There’s a cop out at the end of the story though where the behavior is chalked up to the mystery of how LLMs work… www.rollingstone.com/culture/cult...

I don't know anything about using Mendelian randomisation for casual inference but if your topline results is that drinking champagne causes positive health outcomes I am pretty skeptical of the robustness of your casual identification. www.theguardian.com/society/2025...