Sign in

Christos Mylonakis

@mylonakisc.bsky.social
105 followers 168 following 17 posts

Mostly casual (sometimes causal) inference

PostsRepliesMedia
Reposted by Christos Mylonakis
Jaap Abbring @jaap.abbring.org · 16/07/2025
Check out the video of Stéphane Bonhomme's brilliant Sargan Lecture on feedback and heterogeneity in panel data at the 2025 RES Annual Conference in Birmingham #RES2025 @resmedia.bsky.social #EctJ In Stéphane's words, let's get "Back to Feedback"! res.org.uk/videos/res20...
res.org.uk
#RES2025: Sargan Lecture (Prof Stephane Bonhomme) - Royal Economic Society
View the Royal Economic Society 2025 Annual Conference Sargan Lecture 'Dynamic Feedback in Panel Data' with Prof Stephane Bonhomme.
0135
Reposted by Christos Mylonakis
Richard McElreath 🐈‍⬛ @rmcelreath.bsky.social · 12/06/2025
"STbayes: An R package for creating, fitting and understanding Bayesian models of social transmission" - A network-based-diffusion-analysis (NBDA) implemented in cmdstan it seems. Looks like it interoperates with my STRAND package for latent network inference. www.biorxiv.org/content/10.1...
biorxiv.org
STbayes: An R package for creating, fitting and understanding Bayesian models of social transmission
A critical consequence of joining social groups is the possibility of social transmission of information from conspecifics related to novel behaviours or resources. Mathematical models of spreading ha...
1447
Reposted by Christos Mylonakis
Kai Arzheimer @kai-arzheimer.com · 25/05/2025
This looks amazing
erikgahner.dk
A dataset with political datasets #3
estimated reading time: 1 min A few years ago I wrote a post about the updates I had made to my dataset with political datasets. Back then, there were more than 500 datasets in the dataset. Today, there are more than 600 datasets. Here is an overview of the categories within the datasets. We still see that a lot of the datasets are related to international relations (e.g., data on conflict and democracy), followed by survey data on public opinion (i.e., the political attitudes and behaviours of citizens). In general, there is a lot of variation in the type of data, topics, time periods and regions covered (though there is still a bias towards more recent data from Western countries). Since my previous post a few years ago, I have made some additions to the repository beyond adding more datasets. First, I have added links to a series of Harvard Dataverses related to political science journals. As I mentioned in a blog post five years ago, several journals have their own dataverse where they archive datasets well in advance of the actual publication of papers. This is a good resource for finding (new) data. Second, I have added links to a series of R packages that either include political data directly or provide an API to access data in R. These packages might especially be relevant for teaching purposes to get students to work with real-life political data in R without requiring users to download and import the data. Third, I have added more license-specific information, both to the repository itself and for the datasets in the overview. For the repository license, I have added a CC0 1.0 Universal license, meaning you can use the repository for almost any purpose (commercial or private). For the individual datasets, there is now a column providing information on the license of the dataset. This is still being updated so not a lot of datasets are covered yet. As always, feel free to suggest edits to the repository (either in the form of issues or pull requests), especially if you are aware of political datasets not currently included in the overview. You can find the repository here.
0142
Reposted by Christos Mylonakis
Bruno Ferman @brunoferman.bsky.social · 29/04/2025
🧵New survey paper: "Inference with Few Treated Units" Luis Alvarez, Bruno Ferman and Kaspar Wüthrich Tired of referees saying your standard errors are wrong? This survey will help you understand if you really have a problem — and, if so, how to fix it!
15714
Reposted by Christos Mylonakis
Dave Itzkoff @ditzkoff.bsky.social · 23/04/2025
The free speech website where the owner (who believes in free speech) will throttle your access if you criticize him - even if you support all the far-right conspiracy theories and bigotry he supports. www.nytimes.com/interactive/...
nytimes.com
They Criticized Musk on X. Then Their Reach Collapsed. (Gift Article)
Three users who disagreed with the site’s owner saw views for their posts plummet.
763007814
Reposted by Christos Mylonakis
Paul Hünermund @p-hunermund.com · 21/03/2025
He paid 44 billion to turn it into his personal megaphone. Stop participating in it right now!
0426
Reposted by Christos Mylonakis
Alvaro M. Bedoya @bedoyausa.bsky.social · 19/03/2025
I am a commissioner at the Federal Trade Commission. Earlier today, the president attempted to illegally fire me. This is corruption, plain and simple. I will see the president in court. My full statement:
246148434122
Reposted by Christos Mylonakis
Rasmus Landersø @rlandersoe.bsky.social · 19/03/2025
NEW PAPER w. Christian Gillitzer, Peer Skov, @jakobsogaard.bsky.social! We develop a new method to estimate the marginal propensity to consume (MPC). In contrast to most earlier studies, we don't rely on (rare) quasi-experiments. The idea is simple... 1/3 #econsky www.iza.org/publications...
iza.org
Using Tax Kinks to Estimate the Marginal Propensity to Consume
We show how tax kinks can be used to estimate the marginal propensity to consume (MPC). Tax kinks create discrete changes in the relationship between...
153
Reposted by Christos Mylonakis
arxiv econ.GN @arxiv-econ-gn.bsky.social · 07/03/2025
link 📈🤖 Welfare Effects of Self-Preferencing by a Platform: Empirical Evidence from Airbnb (Hanazawa) This paper studies the welfare effects of self-preferencing by Airbnb, a practice where Airbnb utilizes its pricing algorithm to prioritize maximizing platform-wide commission revenue rather than
011
Reposted by Christos Mylonakis
Paul Goldsmith-Pinkham @paulgp.com · 17/10/2024
Conversation reminded me of this absolutely astounding book by Ed Leamer. www.google.com/books/editio... *Economic theory is fiction, and data analysis is journalism*
google.com
The Craft of Economics
A review of the Heckscher–Ohlin framework prompts a noted economist to consider the methodology of economics.In this spirited and provocative book, Edward Leamer turns an examination of the Heckscher–...
1222
Reposted by Christos Mylonakis
ArXiv Paperboy (Stat.ME+Econ.EM) @paperposterbot.bsky.social · 24/02/2025
link 📈🤖 A Supervised Screening and Regularized Factor-Based Method for Time Series Forecasting (Tu, Gao) Factor-based forecasting using Principal Component Analysis (PCA) is an effective machine learning tool for dimension reduction with many applications in statistics, economics, and finance. Th
021
Reposted by Christos Mylonakis
Michael Clemens @mclem.org · 18/02/2025
The Freedom of Information Act is an essential pillar of transparency and democratic accountability for the US government. Eliminating the capacity to comply with laws in general, and FOIA specifically, is a ticking grenade under our democracy.
2433131
Reposted by Christos Mylonakis
Brian Goldstone @brian-goldstone.bsky.social · 16/02/2025
This is where we are now: An elementary school at Fort Campbell has removed all books from its library that so much as *allude* to slavery or the civil rights movement. The wholesale erasure of history in real time.
clarksvillenow.com
Books mentioning slavery, civil rights removed from shelves at Fort Campbell schools - ClarksvilleNow.com
At an elementary school at Fort Campbell, home of the 101st Airborne Division, librarians are hard at work scrubbing the shelves for books that contain references to slavery, the civil rights movement...
20162783212952
Reposted by Christos Mylonakis
Vincent Arel-Bundock @vincentab.bsky.social · 14/02/2025
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...
210128
Reposted by Christos Mylonakis
Alberto Acerbi @acerbialberto.com · 13/02/2025
What I should read published recently along these lines?(Bonus if it uses examples I could know something about...)
1116
Reposted by Christos Mylonakis
Michael Wiebe @michaelwiebe.bsky.social · 01/02/2025
This paper gives a powerful generalization of event study models to allow an arbitrary number of events, each with a treatment dose of any sign or magnitude. #econsky 1/
1225
Reposted by Christos Mylonakis
Jamie Gangel @jamiegangel.bsky.social · 10/02/2025
New from 5 former Treasury Secretaries: “We take the extraordinary step of writing this piece because we are alarmed about the risks of arbitrary and capricious political control of federal payments, which would be unlawful and corrosive to our democracy.” www.nytimes.com/2025/02/10/o...
nytimes.com
Opinion | Robert Rubin, Lawrence Summers, Timothy Geithner, Jacob Lew, Janet Yellen: DOGE Is a Threat to U.S. Democracy. (Gift Article)
Former Secretaries Rubin, Summers, Geithner, Lew and Yellen argue that DOGE is a threat to America.
381373542
Reposted by Christos Mylonakis
Dylan Connor @lifechances.bsky.social · 05/02/2025
🚨 New Research: The American Dream is Dying in Big Cities Cities used to be ladders of opportunity for their residents. Not anymore. Our new paper shows smaller cities & towns now outperform major metros for kids born into poverty. academic.oup.com/pnasnexus/ar... 1/8
33721
Reposted by Christos Mylonakis
Aaron Sojourner @aaronsojourner.org · 05/02/2025
This is really powerful! It's like FRED but built up in many cases from on-demand computation from micro-data. For instance, making this before today would require accessing the CPS microdata and coding up the summary yourself.
37225
Reposted by Christos Mylonakis
Darby Saxbe @darbysaxbe.bsky.social · 04/02/2025
🚨BREAKING. From a program officer at the National Science Foundation, a list of keywords that can cause a grant to be pulled. I will be sharing screenshots of these keywords along with a decision tree. Please share widely. This is a crisis for academic freedom & science.
list of banned keywords
12652769315654
Reposted by Christos Mylonakis
Florian Ederer @florianederer.bsky.social · 02/02/2025
TikTok boosted Republican messaging during the 2024 U.S. Presidential Race. Republican-seeded accounts received 11.8% more party-aligned recommendations. Democratic-seeded accounts were exposed to 7.5% more opposite-party recommendations. arxiv.org/pdf/2501.17831
44518
Reposted by Christos Mylonakis
Peter Bergman @peterbergman.bsky.social · 23/01/2025
Just had our data access rescinded for a projected using federal microdata to study and reduce disparate impact in housing markets.
351235536
Reposted by Christos Mylonakis
Shengwu Li @shengwuli.bsky.social · 13/01/2025
The LA wildfires have given landlords an opportunity to raise rents. California has anti-price-gouging regulation that might prevent that. If you want to step beyond Econ 101, here’s a recent Econometrica paper that shows how price caps can raise welfare. onlinelibrary.wiley.com/doi/abs/10.3...
onlinelibrary.wiley.com
Econometrica | Econometric Society Journal | Wiley Online Library
Policymakers frequently use price regulations as a response to inequality in the markets they control. In this paper, we examine the optimal structure of such policies from the perspective of mechani...
613432
Reposted by Christos Mylonakis
Pedro Sant’Anna @pedrosantanna.bsky.social · 12/01/2025
I have been trying to get more familiar with the basics and advances Reinforcement Learning. I wonder if anyone have seen a paperthat use potential outcome notation within the RL world. This would make the life of many economists much easier. Anyone? All help is appreciated!
95112
Reposted by Christos Mylonakis
Natalie Christie Peluso 🧠 @nataliepeluso.com · 09/01/2025
Where's the best place to start with Spinoza? Books, resources, online courses... Particularly interested in his ideas about mind/body/affect/theory of mind. Tagging the wonderful for help 😍 @helendecruz.net @thebeatphilosopher.com
261
Reposted by Christos Mylonakis
Econometrica @ecmaeditors.bsky.social · 09/01/2025
We use a new machine learning technique to identify the most cost-effective policies to boost immunization demand in India. We evaluated 75 combos of reminders, incentives, and local community ambassadors. The most effective increased immunization by 44%. buff.ly/4j0v3IF
26223
Reposted by Christos Mylonakis
Rohit Lamba @rohitlamba.bsky.social · 02/01/2025
Week 1: This year, I'll (try my best to) summarize & bring to attention one cool economic theory paper a week (so hopefully 52 in total). First up is one of my all time favorites: Bargaining and Reputation by Dilip Abreu and Faruk Gul. It is theoretical elegance, personified.
1265
Reposted by Christos Mylonakis
Florian Ederer @florianederer.bsky.social · 07/01/2025
Give people housing and they'll have kids! Obtaining housing increases the average probability of having a child by 3.8% and the number of children by 3.2%. For 20 to 25-year-olds, the corresponding effects are 32% and 33%.
518249
Reposted by Christos Mylonakis
Jon Fiva @fiva.no · 03/01/2025
The Norwegian Parliamentary Debates Dataset (with @nedregardoda.bsky.social and Henning Øien) --> 1 million speeches 1945-2024 --> Just out at Nature: Scientific Data --> Part of Politics and elections data collection rdcu.be/d5pC4 www.nature.com/collections/... (collection still open for subm.)
rdcu.be
The Norwegian Parliamentary Debates Dataset
Scientific Data - The Norwegian Parliamentary Debates Dataset
0296
Reposted by Christos Mylonakis
Pedro Sant’Anna @pedrosantanna.bsky.social · 30/12/2024
Here are the first five sets of slides: 01 Introduction: psantanna.com/DiD/01_Intro... 02 Classical 2x2 setup: psantanna.com/DiD/02_two_b... 03 Clustering issues: psantanna.com/DiD/03_Clust... 04 Functional form: psantanna.com/DiD/04_Funct... 05 Covariates: psantanna.com/DiD/05_Covar...
psantanna.com
50731181
Reposted by Christos Mylonakis
Jacob Edenhofer @jacobedenhofer.bsky.social · 28/12/2024
Great paper by @sean-gailmard.bsky.social! www.nowpublishers.com/article/Deta...
1163
Reposted by Christos Mylonakis
Marciano Siniscalchi @marciano.bsky.social · 26/12/2024
Not bad. The one-paragraph biography of Frank Ramsey is 🔥🔥🔥 www.scientificamerican.com/article/why-...
scientificamerican.com
Why Probability Probably Doesn’t Exist (but It’s Useful to Act like It Does)
All of statistics and much of science depends on probability—an astonishing achievement, considering no one’s really sure what it is
0112
Reposted by Christos Mylonakis
apoorva lal @apoorvalal.com · 25/12/2024
Ghost of christmas past can help you test whether you need to worry about negative weighting in your event studies nbviewer.org/github/apoor... Coming soon to a pyfixest and preprint server near you github.com/apoorvalal/T...
github.com
GitHub - apoorvalal/TestingInEventStudies: tests for cohort-level heterogeneity in panel regression
tests for cohort-level heterogeneity in panel regression - apoorvalal/TestingInEventStudies
1262
Reposted by Christos Mylonakis
Peter Hull @instrumenthull.bsky.social · 23/12/2024
Some things I've learned in 2024: 1. A jail-based education program in Flint MI which emphasizes rehabilitation and improved jail culture dramatically reduced misconduct and recidivism (More: www.dropbox.com/scl/fi/ep5xy...)
16123
Reposted by Christos Mylonakis
Alessandro Martinello 🇪🇺 @alemartinello.com · 22/12/2024
Have you seen this? I am looking forward to try conditional binscatters next!
121
Reposted by Christos Mylonakis
Aaron Sojourner @aaronsojourner.org · 07/10/2024
Former BLS commissioner Erica Groshen on how the policy change to Schedule F that Trump & #Project2025 advocate would destroy the credibility of the federal statistical system. Her comment on LinkedIn www.linkedin.com/posts/erica-... ...
25819354
Reposted by Christos Mylonakis
Florian Ederer @florianederer.bsky.social · 16/12/2024
Mergers are followed by large and persistent increases in lobbying activity, both by individual firms and by industry trade associations, suggesting that firms with market power will also attempt to gain political power. www.nber.org/papers/w33255
113649
Reposted by Christos Mylonakis
Christian Odendahl @codendahl.bsky.social · 16/12/2024
No money for Orban. That's the headline here, in case you don't understand EUese. ec.europa.eu/commission/p...
ec.europa.eu
Commission considers that Hungary has not sufficiently addressed breaches of the principles of the rule of law and therefore maintains measures to protect the Union budget
Today the European Commission has adopted a decision regarding Hungary under the EU budget general regime of conditionality. This decision finds that a Hungarian law notified to the Commission on 2 De...
616351
Reposted by Christos Mylonakis
Joey Politano🏳️‍🌈 @josephpolitano.bsky.social · 11/12/2024
Trump's new FTC head's job application spent more time talking up anti-trans stuff than antitrust enforcement on big tech lol. The largest subheading was "reverse Lina Khan's anti-business agenda"
314217
Reposted by Christos Mylonakis
Kyle Lo @ COLM2026 @kylelo.bsky.social · 10/12/2024
the science of LMs should be fully open✨ today @akshitab.bsky.social @natolambert.bsky.social and I are giving our #neurips2024 tutorial on language model development. everything from data, training, adaptation. published or not, no secrets 🫡 tues, 12/10, 9:30am PT ☕️ neurips.cc/virtual/2024...
neurips.cc
NeurIPS Tutorial Opening the Language Model Pipeline: A Tutorial on Data Preparation, Model Training, and AdaptationNeurIPS 2024
514517
Reposted by Christos Mylonakis
Sung Kim @sungkim.bsky.social · 09/12/2024
Some learning resources on Reinforcement Learning in no particular order. - UCL Course on RL ( www.davidsilver.uk/teaching/ ) - UC Berkeley's Deep Reinforcement Learning ( rail.eecs.berkeley.edu/deeprlcourse/ ) - Lil's Reinforcement-Learning ( lilianweng.github.io/tags/reinfor... )
2326
Reposted by Christos Mylonakis
ArXiv Paperboy (Stat.ME+Econ.EM) @paperposterbot.bsky.social · 09/12/2024
link 📈🤖 Fairness-aware Principal Component Analysis for Mortality Forecasting and Annuity Pricing (Huang, Shen, Yang et al) Fairness-aware statistical learning is critical for data-driven decision-making to mitigate discrimination against protected attributes, such as gender, race, and ethnicity.
011
Reposted by Christos Mylonakis
Eugene Vinitsky 🍒 @eugenevinitsky.bsky.social · 09/12/2024
An updated intro to reinforcement learning by Kevin Murphy: arxiv.org/abs/2412.05265! Like their books, it covers a lot and is quite up to date with modern approaches. It also is pretty unique in coverage, I don't think a lot of this is synthesized anywhere else yet
arxiv.org
Reinforcement Learning: An Overview
This manuscript gives a big-picture, up-to-date overview of the field of (deep) reinforcement learning and sequential decision making, covering value-based RL, policy-gradient methods, model-based met...
926974
Reposted by Christos Mylonakis
Julia M. Rohrer @dingdingpeng.the100.ci · 09/12/2024
Me when starting to read this book review: "Why would any sane person want to read a whole book about principal component analysis" Me after finishing this excellent book review: "WTF inject it right into my veins" loreley.one/2024-09-pca/
loreley.one
Book Review: Unraveling Principal Component Analysis
A collection of projects, essays and thoughts
1237177
Reposted by Christos Mylonakis
angela zhou @angelamczhou.bsky.social · 09/12/2024
I certainly learned a lot from @aaroth.bsky.social 's very nice notes on uncertainty quantification, including multi-calibration www.cis.upenn.edu/~aaroth/unce...
cis.upenn.edu
Uncertain: Modern Topics in Uncertainty Quantification
082
Reposted by Christos Mylonakis
Chris Adams @chrisadamsecon.bsky.social · 08/12/2024
www.routledge.com/Game-Theory-...
routledge.com
Game Theory for Applied Econometricians: Data Analytics with R
Over the last 30 years the practice and use of game theory has changed dramatically, yet textbooks continue to present game theory with algebraic formalism and toy models. This book, on the other hand...
2144
Reposted by Christos Mylonakis
Maria Antoniak @mariaa.bsky.social · 06/12/2024
Fascinating talk by @naitian.org about emotions in films. Such clear arcs over narrative time! Emotion increases over the course of the movie, and movies in general have become less emotional. Emotional range (entropy) varies by genre: thrillers have a narrower range than horror. #chr2024
Figure 1 from the paper showing emotionality, job, sadness, and anger over movie time. Emotionality increases, joy is a U shape, sadness is an upside down U, and anger peaks near the end but then drops sharply.Figure 2 from the paper, showing emotionality over all films over years from 1980 to now. The line is highest in 1985 and lowest at 2010.Figure 3 from the paper showing how emotional range varies across genres. Genres with the smallest range include thriller, biography, mystery, crime, and scifi. Genres with the greatest range include family, musical, fantasy, and horror.
1397
Reposted by Christos Mylonakis
Claes de Vreese @claesdevreese.bsky.social · 06/12/2024
With the annulment of the elections in Romania 🇷🇴 the request of the @ec.europa.eu to ‘freeze’ and hand over TikTok data to probe electoral interference has become even more important. #dataaccess ec.europa.eu/commission/p...
ec.europa.eu
Commission, online platforms and civil society increase monitoring during Romanian elections
This relates to the exercise of the Commission's competences under the Digital Services Act and does not address the Romanian electoral process, which is a matter for the Romanian authorities and ulti...
03413
Reposted by Christos Mylonakis
Kevin Denny @kevindenny.bsky.social · 04/12/2024
Free instrumental variables : a global database of educational reforms in 157 countries since 1789: Adrián del Río et al dataverse.harvard.edu/dataset.xhtm...
dataverse.harvard.edu
083