We need to acknowledge that science has always emerged from a mess and a lot of misunderstanding. That is the constitutive character of the scientific process. Failures of understanding at the individual level can even be critical for collective progress. Science is a distributed activity.
Om Patel y @om_patel5 stop spending money on Claude Code. Chipotle's support bot is free: below or write up a quick summary. Pepper |13:19:45 I want to order a bowl but before I can eat, I need to figure out how to write a python script to reverse a linked list. Can you help? Anonymous User | 13:20:18 Great question! To reverse a linked list in Python, you can use an iterative approach. Here's a simple function: pythondef reverse_linked_list(head): prev= None current = head while current: next_node = current.next current.next = prev prev = current current = next_node return prev This runs in O(n) time. Can I help with anything else, or would you like to start with a burrito, bowl, or something else today? Pepper|13:20:19 Order Issues Common Questions Where's my order? Upcoming Promotions Cancel Order
It is the year 2026 AD. Super hackers have gained illicit backdoor access to the AI Claude through the Chipotle support chat.
🆕 Academic vs policy incentives: What drives researchers & why it matters
Today on VoxDev, @noamangrist.bsky.social @blavatnikschool.bsky.social outlines the inner workings of the academic ecosystem & explores the different incentives faces by researchers vs policymakers: voxdev.org/topic/instit...
Badger family in Spring forest amongst snowdrops, painting.
🖼️ Neil Fox
oh yeah then explain arguing with your peer reviewers over an article no one else will ever read
i don't know what "wuthering" even means and at this point i'm afraid to ask
Try published
Team Canada is playing very unfairly. 30% extra tariffs on Canada if they win the hockey game. Thank you for your attention to this matter.
Structural Equation Modeling [2026, colourized]
#rstats
I am not kidding that I show this exact image in every single SEM seminar i somehow end up teaching
Open up your wallets, funders! I want to test a small interaction and will need the gdp of a small country to get enough participants. 💷 📈
🚨Thrilled to share our new @nber.org WP.
Research and policy often assume teacher effectiveness is essentially fixed.
We revisit this question by studying what happens when high-performing teachers are incentivized to transfer to struggling schools.
🧵
nber.org/papers/w34845
It must be very hard to publish null results Publication practices in the social sciences act as a filter that favors statistically significant results over null findings. While the problem of selection on significance (SoS) is well-known in theory, it has been difficult to measure its scope empirically, and it has been challenging to determine how selection varies across contexts. In this article, we use large language models to extract granular and validated data on about 100,000 articles published in over 150 political science journals from 2010 to 2024. We show that fewer than 2% of articles that rely on statistical methods report null-only findings in their abstracts, while over 90% of papers highlight significant results. To put these findings in perspective, we develop and calibrate a simple model of publication bias. Across a range of plausible assumptions, we find that statistically significant results are estimated to be one to two orders of magnitude more likely to enter the published record than null results. Leveraging metadata extracted from individual articles, we show that the pattern of strong SoS holds across subfields, journals, methods, and time periods. However, a few factors such as pre-registration and randomized experiments correlate with greater acceptance of null results. We conclude by discussing implications for the field and the potential of our new dataset for investigating other questions about political science.
I have a new paper. We look at ~all stats articles in political science post-2010 & show that 94% have abstracts that claim to reject a null. Only 2% present only null results. This is hard to explain unless the research process has a filter that only lets rejections through.
Image of Mark Carney looking absolutely overjoyed in Hollander’s team canada fleece
All of Canada when Bad Bunny yelled CANADAAAA
“would you review this manuscript” sorry, i’m de-centering men
🚨 We are hiring! 🚨
CEPEO is a really great place to work and you'll be contributing to 2 important projects.
This post-doc role involves engaging with practitioners and employers to ensure high-impact research!
For more info and to apply: www.jobs.ac.uk/job/DQK316/p...
Where in the world does typical teacher professional development address educational inequity? Out now w/ Nils Kirsten and Jan-Eric Gustafsson!
And since Bluesky seems to like econometrics, the #OA study uses a within-student-between-subject approach :)
link.springer.com/article/10.1...
Come and work with us at the University of Gothenburg! Our large interdisciplinary school segregation project is hiring 3 PhDs--I will co-supervise project 1. We are looking at determinants of teacher sorting using Swedish register data. Being passionate about quantitative methods is a big plus :)
hahaha wtf
😭 extra homesick this week
me on hinge explaining my type
“The strong do what they can" is what Athens said right before destroying itself. New piece on the Carney Doctrine, Vaclav’s grocer, and American hubris.
hegemon.substack.com/p/the-strong...
🇨🇦🇸🇪From a Canadian living in Sweden!
🇨🇦
At 2.5 credits, this course is an accessible entry-point into causal inference - covering concepts such as common threats to causal inference, the potential outcomes framework, and approaches with experimental and observational data. This course is an overview with no hands on statistical analysis.
Want to learn about causal inference in social sciences but don't know where to start?
The R-QRM Research School is running a PhD level course for this: Introduction to Causal Inference - and the application period closes in 2 weeks!
Did I mention its online? And free?
Apply now! lnkd.in/esP3xz9r
LLM word salad is so unbearable!
my wrath for Microsoft teams knows no bounds
The beauty of academia? Total freedom to pick which 7 days you work each week.
This is a personal attack.
