being deployable without having to map face-to-face social network interactions is the main motivation behind algorithms and analysis in “Seeding with Costly Network Information,” Operations Research, 2022 pubsonline.informs.org/doi/abs/10.128… (1/2)

Delighted to share I'll be starting as an assistant professor at LSE Psychological & Behavioural Science LSE in fall 2024. I’m so very grateful to all who have supported me over the years and for this opportunity to continue studying social science and helping to educate the next generations 🎉

Congrats to the excellent Garrett Johnson for getting tenure! Well deserved!

Moral of the story: IV designs have much larger uncertainty + publication bias/file drawer --> Much bigger IV estimates than OLS (with potentially much greater biases).

So excited to welcome Jennifer Allen & Christopher Barrie to NYU's Center for Social Media and Politics! We are incredibly lucky to have both of them joining us -- can't wait to see what we'll accomplish together once they are here!!

Google's Network business extended its decline to seven consecutive quarters in Q1, now representing just 12% of the company's overall advertising revenue. Network also features the lowest margin of Google's advertising businesses. Google's deprecation of third-party cookies may…

I'm in a lot of little fragmented conversations about this case against Meta (which I like to think of as Zuckerman v. Zuckerberg or ZvZ though that isn't the real caption). So here is a brain dump. Corrections welcome, especially from Ethan Zuckerman or Knight First Amendment Institute. 1/

I'm excited to share that I'll be joining NYU Stern as an Assistant Professor in the Technology, Operations, and Statistics group and faculty affiliate of NYU's Center for Social Media and Politics starting in 2025, after a post-doc at Penn with CSSLab at Penn!

I will say it again, statistical power does not care how hard it is to recruit your sample.

Chris Elmendorf Clayton Nall Stan Oklobdzija But Dr. E noticed that a follow-up poll had accidentally hit a bunch of the *same individuals* a second time … and that their stated housing price opinions were often totally different!

“Barely better than chance,” they write

I am not convinced that AI is doing a good job with suggested responses here

Shocking footage shows several officers at Washington University St. Louis beating a professor, slamming him, and dragging his limp body.
SIUE history professor Steve Tamari is reportedly hospitalized with broken ribs and a broken hand.
One doctor told him he's lucky to be alive.

Good moment to reflect on coexistence of monarchies in rich, otherwise-modern countries and AI...

Of course, this Safari-only feature won't apply to ads displayed in the News, Stocks, or App Store apps.

This election truly is THE most important election of our lifetime -- and I mean this as someone who generally poo-poo's that kind of thing.

Chris already wrote a really good thread explaining our new paper on what kind of housing policy voters want. For all the YIMBYs I see on the TL pouring themselves a glass of bleach, I'll offer up some thoughts about why things are not as catastrophic as you might imagine.

I went to MITs recording studio last week and I was sure I was in the wrong place because there were all these high energy laser warnings & bottles of industrial gases in the hallway - no it was the right place.

A few thoughts on:

1) Why 'circling p-values' is a decent heuristic when reading papers

2) Why there is nothing unethical or immoral with criticizing the distribution of p-values a paper reports.

quentinandre.net/post/circling-…

This is a common mistake. If you want to learn how to not be like this reviewer, read lakens.github.io/statistical_in…

'Writing a paper is a vulnerable process. You share ideas, some of them are not going to work out, some of them are not good ideas, you make mistakes, so you need to have a fair amount of trust and a level of comfort with people to work with them.'