Jonathan N. Katz

Welcome! You are invited to join a webinar: A Conversation with Caltech's Jonathan N. Katz: State Redistricting Impacts Around the Nation. After registering, you will receive a confirmation email abou... Please join us on Tuesday, October 28, 2025 at 1:00pm Pacific for the next episode of Election Science Office Hours, a webinar series presented by the Caltech Election Integrity Project and moderated ...

Register here:
caltech.zoom.us/webinar/regi...

#ElectionScienceOfficeHours
@jnkatz.bsky.social @rmichaelalvarez.bsky.social @caltech.edu @caltechlcssp.bsky.social
#CaltechElectionIntegrity

Two women standing on top of a gnarled ancient pine tree on Sentinel Dome with a mountain range viewable in the background

Every Californian with an email address and an internet connection can now visit California’s Bookshelf and access more than 300,000 ebooks and audiobooks.

www.library.ca.gov/uploads/2025...

BOA Boots Are Changing Skiing—So Why Won’t Racers Wear Them? Skiers swear by BOA technology, yet the world’s best racers refuse to make the switch. Do they know something we don’t?

Innovation is afoot in the ski industry.

BOA boots are changing skiing ... and ski racing.
www.skimag.com/gear/boa-ski...

We are very happy to publish the "National Elections Database," including the results of 1,023 presidential and 2,962 parliamentary elections conducted worldwide since 1946!
www.nationalelectionsdatabase.com
with Benjamin Marx and Vincent Rollet

Polls

538-style poll collection has now been recreated by a small group of fans and former staff. all fully transparent and public now. return of live public aggregation is imminent

docs.google.com/spreadsheets...

I got laid off today, with the rest of 18F.

18F was an elite federal software shop. We made gov't websites work better, more efficiently for the American people. We saved taxpayers from getting screwed over by contractors. And were fired for it.

We made this website to tell our story:
18f.org

Graphic promoting data protection efforts. The background features a pattern of yellow, blue, and white triangles. A large navy blue circular overlay at the center contains the message in bold yellow text: "HELP US PROTECT AT-RISK DATA" Below, in smaller white text: "Your contribution TODAY shapes TOMORROW" The University of Michigan ISR logo appears at the top of the circular overlay.

#UMISR: Preserve At-Risk Government Data!

DataLumos, an open-access archive at ICPSR, is working to preserve/share critical govt data. Help keep the data accessible.

Donate: datalumos.org
Explore & contribute: myumi.ch/egrbW
Volunteer: icpsr-data-rescue@umich.edu

#DataPreservation #SocialScience

Rdatasets is a collection of 2300 free and documented datasets in CSV format. It's a great resource for teaching and exploration!

The new `get_dataset()` function from the {marginaleffects} 📦 allows you to search and load them directly in #Rstats.

vincentarelbundock.github.io/Rdatasets/ar...

Steve's Notes on Congressional Politics | Steven S. Smith | Substack Insightful briefs on the politics of the the U.S. Congress. Click to read Steve's Notes on Congressional Politics, by Steven S. Smith, a Substack publication with hundreds of subscribers.

Looking for free, short readings on elements of congressional politics for your course? Check this out. stevesnotes.substack.com

If you have an issue where Dropbox is constantly syncing while @posit.co #RStudio is open, one solution is to run the following code in Terminal:

find "Dropbox" -type d -name ".Rproj.user" -print0 | while IFS= read -r -d $'\0' folder; do xattr -w com.dropbox.ignored 1 "$folder"; done

#rstats

I have even voted on one.

YouTube video by Data Analytics Colloquium Fast ER GPU Accelerated Record Linkage in Python by Dr R Michael Alvarez and Jacob Morrier CalTech

Last week, Jacob Morrier and I presented about work that dramatically speeds up probabilistic record linkage using GPU acceleration. Documentation and code for Fast-ER is available, fast-er.readthedocs.io/en/latest/

But better yet, watch the video!
youtu.be/wsv__0a_KDY?...

Voters are mostly partisans who rationalize, swing voters are often ignorant and voters project their views onto their candidates. But this has always been true! The media was better once, but there was no golden age. Most of their grandparents did not read Walter Lippmann's column.

Very nice example of how useful comparison (or trend calculation) usually needs something more than coefficients. They have a nice page on the general idea that is hidden down in the thread: ourworldindata.org/age-standard...

I'm teaching a grad seminar this winter on Prediction for Decision-making. We'll look at what it means to make good predictions for decision-making from various angles, with a focus on decisions for & about people.

Reading list: statmodeling.stat.columbia.edu/2024/12/06/n...

Suggestions welcome!

Our JSS article is out!

And now I get to focus on {marginaleffects} 1.0.0. Stay tuned.

www.jstatsoft.org/article/view...

This is good advice. People with stable handles, bios, and a post or two present well to would-be followers. Consider also a photo or thoughtful logo of yourself.

If you're interested in trying out LLMs in #rstats but don't know where to begin, I've added a few two vignettes to elmer: elmer.tidyverse.org/articles/elm... and elmer.tidyverse.org/articles/pro...

New notebook:

Sample Size Calculations in #RStats : Money and Power

arelbundock.com/posts/money_...

Political Methodology Join the conversation

Boosting Anton's starter pack to #StatsSky and #polisky. Lots of people worth following here.

bsky.app/starter-pac...

Great to see @aleximas.bsky.social and gang of coauthors measuring salience *independently of choice* with an early well-trained algorithm (from @caltech.edu btw) that predicts visual attention for any image (a la Li and me QJE academic.oup.com/qje/article-...)

After a review process so long and intensive that the title changed twice, I'm excited/relieved that "How to Distinguish Motivated Reasoning from Bayesian Updating" is accepted at @polbehavior.bsky.social.

osf.io/preprints/os...

Here is how it's relevant for your Thanksgiving dinner 🦃👇

Tiny Data, Approximate Bayesian Computation and the Socks of Karl Broman: The Movie This is a screencast of my UseR! 2015 presentation: Tiny Data, Approximate Bayesian Computation and the Socks of Karl Broman. Based on the original blog post it is a quick’n’dirty …

How does Approximate Bayesian Computation *ABC) work? @rabaath.bsky.social has a classic nice simple intro the ABC using the problem of infering the number of socks in a sample of laundry. There's a movie and a page with all the code. www.sumsar.net/blog/2015/07...

Yes, it was an anti-incumbent environment, *globally*—but the US had weathered the pandemic economy so much better than everywhere else, it was totally reasonably to think that the incumbent party could prevail. It was not a forgone conclusion. It was close, but still decisive against incumbents.

Now that @jacksonmatthewo.bsky.social has arrived, it’s a real network

Why we (usually) don't have to worry about multiple comparisons Applied researchers often find themselves making statistical inferences in settings that would seem to require multiple comparisons adjustments. We challenge the Type I error paradigm that underlies t...

Since it is inefficient to attempt to educate every reviewer individually, I am yeeting into your feed this clear paper from Gelman, Hill, and Yajima on how Bayesians can do even better than correcting for multiple comparisons. arxiv.org/abs/0907.2478