Dean Eckles
banner
eckles.bsky.social
Dean Eckles
@eckles.bsky.social

networks, contagion, causality
faculty at MIT

Mathematics 19%
Physics 19%

Reposted by Dean Eckles

Trump issued “a full, complete, and unconditional pardon to all United States citizens” for conduct related to the 2020 election. Now a man facing federal prosecution for voting twice (once in PA and once in FL, both times for Trump) says he's covered and should go free. [VoteBeat] /1
Did Trump accidentally pardon a man accused of voter fraud?
Legal scholars say Trump’s 2020 election pardon may have unintended consequences.
www.votebeat.org
Note that the BBC openly admits in an email to me that the removal of this claim about Trump's world-historical corruption was done "on legal advice."

Translation: Trump's threat of a lawsuit, no matter how bogus, has now been rewarded.

newrepublic.com/article/2036...

Congratulations!

So you're saying Gen AI isn't helping your productivity? :)
Keith and I strengthened our lower bounds for randomized experiments in the linear-in-means model to a general minimax result

Updated results available at arxiv.org/abs/2410.10772
can’t fucking catch a breath

make it stop
ICE deported a woman who owned a home in the US for 30 years. A judge banned ICE from deporting her to Sierra Leone where she had been tortured, so it deported her to Ghana, which kidnapped her and sent her back Sierra Leone anyway. ICE is part of this illegal conspiracy.

Reposted by Dean Eckles

$10.69 for a 15-minute ride?

For visitors, public bikeshare often feels like a ripoff.

In CityLab, I explored why.
Bikeshare Shouldn’t Kick Tourists to the Curb
Barcelona’s bikeshare program excludes non-Spanish visitors. Other cities charge tourists much higher fees to rent two-wheelers. Which policy makes more sense?
www.bloomberg.com
NEW: When Propecy Fails is one of the most famous social psychology books of all time, a look at a small group of UFO believers when the “spacemen” failed to land. I wrote about a new study from an independent researcher who says the book is not what it seems. www.motherjones.com/politics/202...
It’s one of the most influential social psychology studies ever. Was it all a lie?
A classic book on UFO believers and their "cognitive dissonance" after aliens failed to land is called into question.
www.motherjones.com

Reposted by Dean Eckles

Ed, you’ve looked at NVIDA very closely lately and given really good information. Is there any plan to do the same scrutiny on Google and its ai efforts? Google seems to be the only mag 7 company that isn’t circular financing NVIDA and seems to be the company Altman is most concerned about now
“From the night of the massacre onward, Ms. Fletcher was never again able to sleep comfortably in a bed, she wrote…
“When I sleep, it is never very deep or for very long because of the anxiety and the things I see,” she wrote. “Imagine having the same horrible nightmare every night for 100 years.”
Viola Fletcher, Oldest Survivor of the Tulsa Race Massacre, Dies at 111
www.nytimes.com

You've generated an example to haunt diff-in-diff believers

And it would be even more credible imo without the gap, even if it looks approximately additive

OK but maybe you find the point persuasive that past coverage of internal research has been actively misleading about what we can conclude from it, so we might want to cautiously interpret new claims about what such research shows

I'm a big fan of actually plotting unnormalized trends of the treated and control groups. So often diff-in-diff is leaning really heavily on parametric assumptions to extrapolate. cf statmodeling.stat.columbia.edu/2023/08/22/t...
thefacebook and mental health trends: Harvard and Suffolk County Community College | Statistical Modeling, Causal Inference, and Social Science
statmodeling.stat.columbia.edu

The cited survey data had more teen girls saying
Instagram made them feel better than worse...

Would be interested to learn more... Like this prior headline was based on research that was quite ambivalent.

Maybe useful to compare with papers.ssrn.com/sol3/papers.... which does have some discussion of effects you might expect under different, changing economic conditions

Looking at the time series, this looks more credible than many difference-in-differences analyses.

So a good reminder that causal inference is hard — especially with a single treated unit.

Also, showing the non-scaled ZORI would probably reveal the parametric extrapolation diff-in-diff does here.
I think this is mostly San Francisco finally shrugging off the pandemic, but it is *really* funny that rent prices in San Francisco shot up *immediately* after the city banned RealPage and other algorithmic price setting software.

My pre trends are incredible!

Reposted by Dean Eckles

I think this is mostly San Francisco finally shrugging off the pandemic, but it is *really* funny that rent prices in San Francisco shot up *immediately* after the city banned RealPage and other algorithmic price setting software.

My pre trends are incredible!
If you're trying to convince your friends to spend time on Bluesky rather than X, maybe show them this. X is not "the public town square" or about "free speech." It's "just what Elon Musk wants you to see." If you see stuff he doesn't like he'll step in to make sure you don't see it for long.
If you scroll on X, you are only being shown what Elon wants you to see. If you create content on X, no one will see it unless Elon wants them to.
ICE’s Detention Center outside Chicago was sued on October 30 for allegedly abusing detainees. One day later, a "system crash" lost all video footage that could have shown how detainees were being treated. trib.al/QwT3aqI
THREAD: Judge Ellis is the first federal judge to review extensive body cam video of DHS's actions in Chicago. She finds that DHS *repeatedly* misled the public and made claims that were disproven by agents' own videos.

I'll go through some of the most egregious ones here.

"People buy GPUs like they buy eggs. You don't buy just one."

Reposted by Dean Eckles

Factor analysis and varimax have been widely misunderstood among statisticians. Two years ago, Muzhe Zeng and I had a discussion paper at JRSS-B that tried to clarify why factor analysis and varimax were actually decades ahead of their time

It’s free (with discussion) here:
doi.org/10.1093/jrss...
Vintage factor analysis with Varimax performs statistical inference
Abstract. In the 1930s, Psychologists began developing Multiple-Factor Analysis to decompose multivariate data into a small number of interpretable factors
doi.org
RFK Jr had committed to Bill Cassidy, as a condition to win his vote, that he would keep website language.

Cassidy in February: “If confirmed… CDC will not remove statements on their website pointing out that vaccines do not cause autism.”

Note the language in second photo.
Amazon sues Perplexity over their agentic browser Comet using Amazon to make purchases for users. Might be an interesting case to keep an eye on www.theguardian.com/technology/2...
Amazon vs Perplexity: the AI agent war has arrived
A lawsuit over automated shopping reveals a deeper struggle over who will control the next generation of AI and what happens when autonomous agents start acting on our behalf
www.theguardian.com
Just wanna re-up in simple terms that when Biden talked to platforms, Jim Jordan launched years of investigations into everybody involved, said it was tyranny, censorship, etc.

And now they just straight up acknowledge that they talk to platforms too.

www.washingtonexaminer.com/news/crime/3...
DHS playing 'whack-a-mole' shooting down made-up ICE stories
The Department of Homeland Security is stepping up efforts to combat fake news, viral AI videos, and misinformation on ICE and Border Patrol.
www.washingtonexaminer.com
The actual secret to why I know stuff is that I ask a question any time I don’t understand literally anything. I don’t care how simple it is. Anybody who makes fun of you for asking a simple question likely doesn’t know the answer either