Data Science Team Training: Building data science capacity in the public health workforce. I'm writing a (free) e-book for public health practitioners upskilling in data science, as part of my work with the CSTE's DSTT program. blog.stephenturner.us/p/data-scien...

foster care has been on the decline nationally over the past ten years. that's a good thing! but there's a group that routinely argue that this is putting kids in danger. @kelleyfong.bsky.social; @bobapel.bsky.social and I checked the evidence (it's null 1/n) jamanetwork.com/journals/jam...

News coverage of the Trump administration's proposed "compact" with universities has been, so far, shockingly bad. I hate to pick on NPR reporter Elissa Nadworny, who's usually a solid reporter, but almost every important thing I heard her say this morning about the proposed "compact" was false.

1/ Do body-worn cameras (BWCs) improve public attitudes toward the police? Or is how officers treat people what really matters? My new Justice Quarterly article with Mustafa Demir from John Jay tackles these questions with a vignette experiment. 🧵

I’ve watched with interest as the number of ASC divisions has grown over the course of my career, from 4 to 21. I’m now tempted to start a petition to create an all-new division: Division of Criminology. Curious if there would be any takers.

1/ Can a Google search hurt your chances of getting a job more than a background check? A new study with Sarah Lageson on criminal records, race, and willingness to hire has surprising answers. 🧵

The political theory behind IRA was roughly as follows: We have lost control of the information landscape and can no longer win rhetorical or purely political battles; however, if we make substantive policy progress that directly touches voters' lives, they will notice and reward us.

The menswear guy: social theorist. Some interesting history and sociological insight here.

Enjoyable for those interested in history of urban issues. With some justified finger-wagging at Jane Jacobs for hypocrisy: “It was the kind of thing that Jacobs praised, but when she buys the building, she gut renovates it. She tears out the storefront. She turns it into a single-family home.”

Ok sociology, what do you think are genuine breakthroughs that our field has made. Contributions that might convince skeptical but sympathetic *academics* (not the public) of the value of our field? I'll brainstorm some of mine in the thread - I treat sociology very broadly

"Fiscal Centralization and Inequality in Children's Economic Mobility" New research with @schechtlm.bsky.social @zparolin.bsky.social just out in ASR doi.org/10.1177/0003... #sociology #demography #econsky

NEW: René D. Flores, Edward Telles, Ilana M. Ventura, "New OMB’s Race and Ethnicity Standards Will Affect How Americans Self-Identify"

Here's a fun way to encourage students to always look at their data. A few years ago, I wrote a script that converts a black and white png to data and plots it.

I've just finished the annual update of our curated links on the Development Impact blog, which sort key posts from the last 13 years. First up, technical topics and methods: how to do RCTs, power calcs, DiD, IV, RDD, PAPs, publication, analysis issues, and more: blogs.worldbank.org/en/impacteva...

From Jonathan Roth on X: I have created a #DiD Resources page on my website. It has links to all of my DiD teaching slides, coding exercises, and packages I've created. All this info was technically already online, but hopefully this makes it easier to find it! www.jonathandroth.com/did-resources/

I wrote a small r-script to download the SEER county-level population age/race data (single age year and grouped years), break the string apart, and create a full dataset. Is that something people want? I can post it on GitHub.

I’m releasing ISOCODES, a new Stata package to generate standardized country code variables.   Feed in a string variable identifying countries and isocodes outputs numeric/2-3 letter codes (ISO3166) or full country names.   I’ll give you a short motivation and rundown below.

Social scientists need to write papers but we generally aren't taught how to actually do that. Here is how I get papers out the door, in 10 straightforward steps. 1/N #econsky #socsky #scisky

In today's print edition: www.theglobeandmail.com/opinion/arti...

Last Fall I completed another iteration of Gov 50 (Data Science for the Social Sciences), and I've been really happy with the course. We doubled in size to 250 students and got great reviews from students. What's worked for us? gov50-f23.github.io

💡Glad to see this paper with Beyers Louw finally published: "On the Nuisance of Control Variables in Causal Regression Analysis" (preprint available on arXiv). doi.org/10.1177/1094...

So excited to announce that our textbook with Xavier, "Difference-in-Differences for Simple and Complex Natural Experiments", is now under contract with Princeton University Press. Check out the "working textbook" version here! Comments welcome! papers.ssrn.com/sol3/papers....

Alarming just how readily pharmacies can give away private information without as much as a warrant

Well I guess when you put it that way…

Empiricism xkcd.com/2855

#30DayMapChallenge #2 lines I revisit one of the coolest small improvement one can do to their maps – create borders explicitly as lines and not as polygon outlines💡 #rstats #rspatial #dataviz Blog post: ikashnitsky.phd/2023/map-bor...

This is a lot of fun for anyone who is interested in the dynamics of neighborhood and place, as well as anyone who has lived in New York City.

This is absolutely terrific, and highly recommended for an intro class or any class that concerns data and measurement. It’s just 30 minutes long.

Econometric Thread (#EconSky): Today, I will briefly discuss a few recent papers expanding the synthetic control method (SCM). I will talk about three WPss: Abadie + L'Hour (2019), Grossi, Lattarulo, Mariani, Mattei + Oner (2020); Cao + Dowd (2019) and Cattaneo, Feng, Palomba +Titiunik (2023).

Econometrics Thread: Marginal Treatment Effects (MTE) Today, I will explain the basics of MTE and will mention the papers that I believe to be important. As my wife says, I like to preach and spread the Gospel of MTE. (PS: I'm moving some of my Twitter threads to here.)

a database of datasets ⬇️ been working for awhile on pulling together economic datasets for econ & policy students b/c there is *so* much publicly available data sharing it for anyone who finds it useful pls suggest additions; work in progress lenorepalladino.notion.site/Economic-and...

📈📉 #econsky I'm teaching causal inference and want to give students an example of data+code using the new DiD TWFE estimators. (My examples use proprietary data or do not rely on TWFE.) Thanks team!

Always happy to help 😘 here is the canonical paper on posttreatment bias, highly recommended: onlinelibrary.wiley.com/doi/full/10....

A welcome installment in the search for the One True Cup of Tea along with the One True Biscuit. Science never sleeps—due, in part, to its being over-caffeinated.

“Recall that the original Luddite movement coincided with the revolutionary fervor that was sweeping Europe in the early 1800s. Decel movements may simply be a way of crying ‘Stop the bus, we want to get off!’.”

NEW: U.S. states lock up Black people at 6x the rate of white people, on average. We just published updated 50-state data on incarceration rates by race, as part of our mission to make important data about the criminal legal system accessible to everyone: www.prisonpolicy.org/blog/2023/09...

Guess I should post something here, so I’m linking my job market paper! I examine the effects of ideological polarization on local politics through the lens of police union endorsements. tinyurl.com/2s7kdpem

Running shorts need a different phone pocket in the liner. If I’m sweaty or it’s raining, the mesh goes to work swiping. I’d like to apologize to my brother, friend, colleague, and research assistant for the calls. And to the Uber driver for the canceled trip that cost me $5.