Jonathan Horowitz
jonathanhorowi1.bsky.social
Jonathan Horowitz
@jonathanhorowi1.bsky.social
Sociology sometimes. Goal is to be the most boring poster on the internet. I can't believe I have to say this, but these views are mine alone.
And second, this symposium where somehow they somehow got 15 well-known scholars to respond to a polemic written by Deaton and Case arguing that RCTs are just not that good. I think the exchange is very interesting.
www.sciencedirect.com/journal/soci...
Social Science & Medicine | Randomized Controlled Trials and Evidence-based Policy: A Multidisciplinary Dialogue | ScienceDirect.com by Elsevier
Read the latest articles of Social Science & Medicine at ScienceDirect.com, Elsevier’s leading platform of peer-reviewed scholarly literature
www.sciencedirect.com
November 11, 2025 at 11:15 PM
Now that I think of it, this was also something that came up when we were reimagining our quant methods reading list for the comprehensive exams. There were two things I suggested: first, Cinelli and Hazlett's paper on sensitivity tests for omitted variable bias:
academic.oup.com/jrsssb/artic...
Making Sense of Sensitivity: Extending Omitted Variable Bias
Summary. We extend the omitted variable bias framework with a suite of tools for sensitivity analysis in regression models that does not require assumption
academic.oup.com
November 11, 2025 at 11:15 PM
This one is an important correction to the narrow focus of most of the "causal inference" literature. (cc: @davebrady72.bsky.social)
www.degruyterbrill.com/document/doi...
The necessity of construct and external validity for deductive causal inference
The Credibility Revolution advances internally valid research designs intended to identify causal effects from quantitative data. The ensuing emphasis on internal validity, however, has enabled a negl...
www.degruyterbrill.com
November 11, 2025 at 11:03 PM
"Many models regress the first-differenced outcome on end-of-period covariates, which violates the temporal order."

They did what!?
November 11, 2025 at 7:16 PM
There are certain classical liberal arts disciplines that you cannot run a university without, and they often score badly on these metrics because the research is obscure and they don't have a lot of majors. But without statistics, philosophy, and history you can't really understand anything else.
November 11, 2025 at 4:21 PM
It's implied based on the clothes but not spelled out. Quite subtle. Billy Bragg is great at giving depth to the story with little details that are very subtle while hitting you over the head with something else.
November 11, 2025 at 4:06 PM
I love this song but as an example of downward mobility it's kind of iffy.

It is, however, a fantastic example of labor market queues and how someone who is a good worker can't get a second look when others "look the part."
November 11, 2025 at 3:59 PM
I like this example because it is one of the only examples I can think of that really hits the them of *downward* mobility hard.
November 11, 2025 at 3:53 PM
The most revolting example of this IMO is the music video for Damian Marley's "Living it Up," which is the definition of someone being *so close* to understanding what's at stake before pulling a complete 180.

www.youtube.com/watch?v=8XN8...
Damian "Jr. Gong" Marley - Living It Up (Official Video)
YouTube video by Damian Marley
www.youtube.com
November 11, 2025 at 3:45 PM
My guess is that if I asked anyone other than underground hip-hop fans to name 10 rappers off the top of their head that all 10 would have multiple songs that basically say this. Look at where we came from and look at how rich we are now!
November 11, 2025 at 3:38 PM
OTOH Thanksgiving in Southern Ontario feels like "Fall in Wisconsin" and not "The Arctic in November"
November 1, 2025 at 7:18 PM
When I moved to Canada I had to get used to the idea that Thanksgiving was no longer a buffer between Halloween and the dreaded Christmas Music
November 1, 2025 at 7:17 PM
It would be great to have more sociology-economics collaborations, but I think it would be hard. Economics has a much narrower sense of what constitutes a useful research study, especially with causal arguments. I'm perfectly fine with saying "this could be wrong in case X" in my manuscript.
October 29, 2025 at 5:11 PM
My impression is that development economists, economist demographers, and (some) labor economists and economic historians overlap with quantitative sociology. But much of "mainstream" economics feels like a bunch of instrumental variables looking for a use case.
October 29, 2025 at 5:00 PM
Al Green. He was so good (might still be, IDK).

I might go with The Kinks but I'm pretty sure I would have to explain the name to someone (which was probably intentional on their part). NBD in 2025, but in 1975 I don't want to do it.
October 27, 2025 at 3:26 PM
Grammar check is the one thing big thing on this list that I agree with. Grammarly-type stuff can be very useful. I'm not sure really what "doing your own editing" means in that context though!
October 24, 2025 at 4:15 PM
I think there's also a place for Rose the Hat, although without the knowledge of what she is it would go over most people's heads.
October 23, 2025 at 5:04 PM