Just don't run predictive margins!! They are not the same!
15.10.2025 18:53 β π 3 π 0 π¬ 0 π 0@asacarny.bsky.social
Associate Professor @columbiahpm.bsky.social visiting this fall @beckerfriedman.bsky.social. Also @nber.org & @j-pal.bsky.social. Economics & health policy. #econsky #healthpolicy #medsky ππππ½π³οΈβπ http://sacarny.com Posts represent my views, not my employer's
Just don't run predictive margins!! They are not the same!
15.10.2025 18:53 β π 3 π 0 π¬ 0 π 0Toying around with this yesterday in Stata, clogit, xtpoisson, and ppmlhdfe were pretty similar in speed. But I just had one level of fixed effects (the group id). I would bet if you have additional fixed effects in the regression ppmlhdfe is far superior.
15.10.2025 18:52 β π 1 π 0 π¬ 0 π 0See journals.sagepub.com/doi/abs/10.1...
15.10.2025 18:29 β π 0 π 0 π¬ 0 π 0Fun fact: you can estimate a conditional logit by running a fixed effects Poisson. They yield the same estimates and standard errors - they maximize the same likelihood. Poisson regression forever!
15.10.2025 18:27 β π 60 π 10 π¬ 6 π 2@instrumenthull.bsky.social where are we on this?
14.10.2025 17:30 β π 1 π 0 π¬ 0 π 0lol he is???
11.10.2025 02:53 β π 1 π 0 π¬ 1 π 0Also hopefully not a βDoctor Mike Reacts to Confused Health Economistβ video situation
11.10.2025 02:52 β π 1 π 0 π¬ 0 π 0Not everyone in the US knows each other Rafe!!
11.10.2025 02:51 β π 1 π 0 π¬ 1 π 0Only in the sense that the algorithm is pushing me his entire repertoire
11.10.2025 02:49 β π 1 π 0 π¬ 2 π 0As someone on the Pitt to ER pipeline I strongly recommend this (now burning through ER season 8)
11.10.2025 02:48 β π 2 π 0 π¬ 0 π 0Doctor Mike!!! Let this be your introduction to the broader Dr Mike commentary universe
11.10.2025 02:45 β π 1 π 0 π¬ 1 π 0Very excited this is coming out soon!
cc @ambarlaforgia.bsky.social
I thought I'd put the administration's proposed "compact" with universities in context, so I wrote the blog post below.
It's especially for journalists covering this story!
Many details about how the compact itself works and why the administration has retreated to this strategy.
The 2025 academic econ job market is trending better than the first COVID market year but worse than the rest of 2019-present
www.davidvandijcke.com/joe_tracker/
I think at Mailman at least there is an opportunity to request an extension, it isn't automatic. Just based on an email I saw from earlier this year. I'm not sure how hard it is to actually get the extension
12.09.2025 17:06 β π 1 π 0 π¬ 0 π 0Screenshot from the movie Speed of the bus making a high-speed turn surrounded by police vehicles
The bus I've been taking this week makes local stops then runs on the highway. Like the bus in the movie Speed. It's all I can think about on my way in.
11.09.2025 15:22 β π 1 π 0 π¬ 0 π 0Out today in @jamapsychiatry.com: we find that inpatient psychiatric bed supply increasingly comes from freestanding psychiatric hospitals in large for-profit chains.
Authors: Karen Shen @johnshopkinssph.bsky.social Mark Olfson @columbiapsych.bsky.social + me
jamanetwork.com/journals/jam...
Selfie of me smiling in front of the Broad Street pump
Yesterday I had the privilege of visiting the Broad Street pump! Sadly, I saw that the pump handle had been removed. I worked to reinstall the pump handle so local residents would not be deprived of this vital resource. So glad to bring some of the latest American public health ingenuity to London!
05.09.2025 12:38 β π 48 π 9 π¬ 4 π 0August 1, 2025 AMERICAN ECONOMIC ASSOCIATION Committee on Economic Statistics and Committee on Government Relations Statement from the American Economic Association on the Dismissal of the BLS Commissioner Leaders of the American Economic Association express their grave concern over the dismissal of the Commissioner of the Bureau of Labor Statistics (BLS) earlier today. The independence of the federal statistical agencies is essential to the proper functioning of a modern economy. Accurate, timely, and impartial statistics are the foundation upon which households, businesses, and policymakers make critical decisions. Undermining the independence or credibility of these agencies threatens the integrity of the information that markets, institutions, and the public rely on every day. Measuring the vast and dynamic U.S. economy in real time is inherently challenging. It is standard practice for statistical estimates to be revised as more complete and higher-quality data become available. These revisions reflect the commitment of statistical agencies to accuracy, transparency, and methodological rigor-not failure or bias. The BLS has long had a well-deserved reputation for professional excellence and nonpartisan integrity. Safeguarding this tradition is vital for the continued health of the U.S. economy and public trust in our institutions. We call upon elected officials to respect and preserve the independence of the nation's statistical infrastructure. Lawrence Katz President, American Economic Association Katharine Abraham President-Elect, American Economic Association Karen Dynan Chair, American Economic Association Committee on Economic Statistics Kenneth Troske Chair, American Economic Association Committee on Government Relations
Statement from the largest economics association about the BLS firing
As context: AEA approximately never makes such public statements
This is a big deal
Congrats Arrianna!!!
31.07.2025 23:27 β π 1 π 0 π¬ 0 π 0News reports say Columbia paid a "fine" of $200 million, which is grossly excessive, given the lack of any government authority to impose such a fine. On the blog, I parse the agreement and the stakes to explain what the dollar figure really reflects and its ominous implications. π
24.07.2025 13:33 β π 105 π 33 π¬ 10 π 12Characteristically clear-eyed thinking on the dangers of "regulation by deal" from my colleague David Pozen. balkin.blogspot.com/2025/07/regu...
24.07.2025 01:49 β π 51 π 20 π¬ 0 π 1Yes!!!!!
14.07.2025 18:50 β π 3 π 0 π¬ 0 π 0Great rejoinder to a WSJ letter that (IMO quite incorrectly) interpreted the Oregon Health Insurance Experiment as showing that Medicaid doesn't improve health.
www.statnews.com/2025/07/03/o...
If you end up using it please let me know how it goes! It seems like the RxNorm data is good for this application but would love confirmation...
30.06.2025 18:34 β π 1 π 0 π¬ 0 π 0Trying to identify opioids and other drugs in pharmacy data (claims, PDMP, etc.)? Use my code to quickly build a list of national drug codes (NDCs) using the free public database RxNorm.
I wrote this code to replace the CDC's now-discontinued opioid NDC dataset.
github.com/asacarny/dru...
My HCRIS hospital cost report code + data is updated through 2024! I threw the switch and moved everything to R. The new code lets you pull variables from the alphanumeric file, like hospital names and IDs.
NB: I'm using this data now but pls think of it like beta testing.
github.com/asacarny/hos...
A lot of you have been asking how my 10 million beneficial nematodes are doing. Well the answer is that me and my 10 million microscopic sons are doing great! Thanks so much
26.06.2025 21:17 β π 7 π 1 π¬ 0 π 0Currently in an ASHEcon session where my collaborator will be presenting our paper so Iβm covering my name tag and whispering to people in the audience that I heard the last paper is really good with a very solid identification strategy
23.06.2025 21:07 β π 18 π 0 π¬ 0 π 0Just amateur horticulture
16.06.2025 19:52 β π 1 π 0 π¬ 0 π 0