Aditya Dasgupta

Fair enough, it's the widespread leap from that to -> inference about real-world equilibrium behavior/outcomes that perturbs me but I can see how that's an improvement as far as trying to model the individual process of political cognition

I can appreciate that. What do you see as an example of a topic where survey experiments have greatly improved knowledge greatly over the old approach? Asking out it curiosity as I come at the whole thing from a CP/PE as perspective opposed to behavior

Excited to post the latest version of my JMP: The female labor supply constraints of spousal jealousy bit.ly/4nn9apn

I use two field experiments to study the role of spousal jealousy in constraining married women’s employment. More below 👇:

I agree with this — survey experiments represent a different intellectual lineage from usage of natural experiments to overcome real-world endogeneity (credibility revolution). That said, I think collective confusion that randomization=credible has given survey experiments too much epistemic status

> Between 1995 and 2021 (our sample period), there were a total of 47 individuals who have been a congressional leader; 20 of whom made stock trades both before and after ascension to leadership.

Curious to read your reasoning. Mine: 1. informational equivalence effectively makes them observational quite often: 2. credibility revolution was about empirical strategies to overcome real-world endogeneity, survey exps do opposite, identification by removing realism

I agree with this 100%

I wouldn't disagree in principle, it would just seem rare in practice in social science that there aren't plausibly many open backdoor paths paths or reverse causality between X and Y...? especially when it comes to 'big' variables we typically care about

This is about to radicalize me against the credibility revolution

Go home prediction markets: you’re drunk

Political prediction markets moved billions in 2024, but new evidence shows they weren’t very accurate or efficient

PredictIt beat chance 93% of the time

Kalshi? 78%

Polymarket? 67%

Big price divergences, weak/negative correlations, & rampant arbitrage

the case for slower, better/more careful research papers in poli sci gets another data point in its favor

thanks for reading and glad you found it interesting…!

incredible that we can turn correcting coding errors into litigation about the process in which we are allowed to transmit this information

I mean, come on, there are some unambiguous howlers -- just errors, not matters of debate -- identified in the replication paper and it should be OK to say so without all kinds of hand wringing about the process

Seems perfectly fine in any discipline that purports be a science and not an honor culture. Surely we need to speed the production of replications and not restrict it by imposing various restrictions and, as you are doing, casting aspersions around tone

Important public good (replications are much needed to help keep the whole enterprise honest but under-supplied)

💡 How does moving to opportunity reshape political behavior?

🗞️ In our new BJPolS paper, @thmskrr.bsky.social and I show that residential relocations that increase access to opportunity foster political integration and shift political preferences to the left.

👉 tinyurl.com/46utjj65

The potential existential threat of large language models to online survey research | PNAS The advancement of large language models poses a severe, potentially existential threat to online survey research, a fundamental tool for data coll...

Many have asked for the LLM Survey paper. The release was bungled a bit by PNAS, but it is live now: www.pnas.org/doi/10.1073/...

Thanks!

Ireland winning goal and end of match with Irish commentary

thanks..!!

thanks!

thanks!

thx!

very interesting..! thx

Happy to learn I received the Michael Wallerstein prize in political economy for this article on the political consequences of technological change in agriculture in the US: www.cambridge.org/core/journal...

What's the evidence for long-run jati endogamy? Is there a paper you have in mind? (Asking out of curiosity -- would like to read it)

thx!

Do architecture and urban planning affect political behavior? Happy to share a paper that @tesaliarizzo.bsky.social and I have coming out at the APSR which uses computer vision to investigate how the built environment shapes inequalities in civic participation in Mexico: osf.io/preprints/so.... 🧵1/5

The findings show that the built environment exerts an important on inequalities in civic participation. We also provide a new way of using computer for inductive inference for image data. 5/5