The estimate is in the design On stacking, discrete outcomes, matched inference, and data-driven controls

Hello, we have a new post :)
Different control sample, different sign
Different outcome type, different estimand
Different matching procedure, wrong SEs
Four papers on why DiD estimates depend a lot on the choices you make before running your code
www.diddigest.xyz/p/the-estima...

The outcomes you measure and the assumptions holding them up New papers on compositional shifts, coarsened outcomes, pre-trend testing and event-study identification

We have a new post :)
Ever wondered what happens when your DiD sample composition shifts over time?
Or what “parallel trends” means when outcomes are rounded into intervals?
Or whether your pre-trend test is actually testing what you think it is? www.diddigest.xyz/p/the-outcom...

My friend Xu has a WP out!
He and prof Zhengwei use CEPS data to show private tutoring exacerbates inequality via the "rat race": intense competition degrades class atmosphere and demotivates non-tutored peers, causing them to give up
Link here papers.ssrn.com/sol3/papers....

Really enjoyed this, thank you!!

The American Math Crisis

I was glad to be on the latest episode of @dkthomp.bsky.social's Plain English podcast, discussing how to turn around declining US math skills.

We know at least some of the solutions but in many cases have been doing just the opposite.

Listen here:

open.spotify.com/episode/06Ve...

We have a new (different) post :)
www.diddigest.xyz/p/on-finding...

Hidden Bias, Pie Charts and Spillovers What to consider when reality has stopped cooperating

We have a new post!
- Bounding DiD estimates when unobserved confounders exist,
- Running DiD on categorical outcomes that must sum to one, and
- Estimating treatment effects when your units are connected in a network (interference + spillovers)
www.diddigest.xyz/p/hidden-bia...

Missing, Messy, and Misweighted A DiD horror story?

Job-market candidates or job-market candidates' advisers, I'm re-upping this because I want to read (and write about) your theory/applied DiD job-market paper :)
Please send it to me 🙏
www.diddigest.xyz/p/missing-an...

Counter factual??? You mean FAKE NEWS???

Amazing paper (and findings!)

Unlocking college potential: The role of student expectations and non-cognitive skills in college success Attending college is a significant human capital investment, but only about 60 % of those who start college will have a completed degree six years lat…

60% of U.S. students who start college finish within 6 years
• Non-cognitive skills shape grade expectations & performance
• But don’t predict graduation
• Many students misjudge future performance

By @gzamarro.bsky.social , Nichols, Trivitt, Djita
sciencedirect.com/science/arti...

Where Standard Assumptions Go To Die Universal treatments without clean controls, continuous policies without untreated groups, reversible reforms over time and statistical inference with handful of cases

We have a new post!📬
⭐️Factorial DiD (Xu, Zhao & Ding)
⭐️DiD With No Untreated Units (de Chaisemartin et al.)
⭐️Treatment Effects in Complex Designs (de Chaisemartin & D’Haultfœuille)
⭐️Inference With Few Treated Units (Alvarez, Ferman & Wüthrich)
diddigest.substack.com/p/where-stan...

How market design can feed the poor America's largest non-profit had a broken distribution system. University of Chicago economists fixed it.

Very interesting post on how the non-profit Feeding America implemented an auction system with its own currency which massively improved allocation of food to food banks.

www.worksinprogress.news/p/how-market...

Loooove to learn about model misspecification 😍

The Chamberlain Seminar continues this semester with two exciting online sessions on 9/26 & 10/31! Check out the details below and click below to join our mailing list!

mailman.stanford.edu/mailman/list...

🚨 We have a comment on Begum et al (2018) forthcoming in @readdemography.bsky.social - see link below! @i4replication.bsky.social

Work-from-Home as a Lever Against the Motherhood Penalty Emma Harrington and Matthew Khan recently posted their paper "Has the Rise of Work-from-Home Reduced the Motherhood Penalty in the Labor Market?" as an NBER working paper. I first encountered this pap...

Some thoughts on Emma Harrington and Matthew Khan's recent NBER paper "Has the Rise of Work from Home Reduced the Motherhood Penalty in the Labor Market?" www.nber.org/papers/w34147

open.substack.com/pub/dismalsc...

Why Does Value-Added Work? Implications of a Dynamic Model of Student Achievement Founded in 1920, the NBER is a private, non-profit, non-partisan organization dedicated to conducting economic research and to disseminating research findings among academics, public policy makers, an...

Why Does Value-Added Work? Implications of a Dynamic Model of Student Achievement www.nber.org/papers/w34119

"Although conventional value-added estimates are biased for individual teachers due to attenuation, we find they are forecast unbiased when applied across a sample of teachers"

CRISPR as a microbial immune system In 2003, Mojica wrote the first paper suggesting that CRISPR was an innate microbial immune system. The paper was rejected by a series of high-profile journals, including Nature, Proceedings of the National Academy of Sciences, Molecular Microbiology and Nucleic Acids Research, before finally being accepted by Journal of Molecular Evolution in February, 2005.[3][4]

TIL the original paper describing CRISPR, by Francisco Mojica, was rejected by 4 journals and took 2 years to be published

New issue of Journal of Economic Perspectives is out. Quite timely piece on Fed independence.

pubs.aeaweb.org/doi/pdfplus/...

Automatic follow :) thank you!

Who’s this queen??

Parallel Trends… Conditionally: Covariates, Violations, and More Robust DiD Methods The devil in the ~DiD details~

We have a new post🎈
Why your covariates might be "lying" to you and other tales from the "identification frontier":
✅ CBPS-DiD for model misspecification
✅ When good controls go bad (CCC violations)
✅ Bayesian sensitivity for PT violations
open.substack.com/pub/diddiges...

Parallel Trends… Conditionally: Covariates, Violations, and More Robust DiD Methods The devil in the ~DiD details~

We have a new post🎈
Why your covariates might be "lying" to you and other tales from the "identification frontier":
✅ CBPS-DiD for model misspecification
✅ When good controls go bad (CCC violations)
✅ Bayesian sensitivity for PT violations
open.substack.com/pub/diddiges...

Data come in many different formats and are used in many different ways, but in many cases, a checklist like this (along with good data documentation) can help you verify if a dataset is in a usable format for most general purposes.
osf.io/t8upr

🚀Be part of the next round of the Women in Economics Mentoring Programme — a unique opportunity that connects early-career women economists with experienced mentors.

🎯 Programme duration: October 2025 – July 2026
📆 Deadline to apply: August 31st
👉 Apply now: form.jotform.com/251723111137...

Happy to participate!
You can register to attend here:
www.tickettailor.com/events/irish...

Wokeness: a Retrospective In recent times my online sphere has had a fair few people make the claim that, in some sense, the culture has moved on from Woke. The d...

My Retrospective on Wokeness in detail! Blogs are for just saying stuff, after all. So here is my attempt to say what was distinctive (if anything) about a recent era of socio-cultural life, what (if anything) changed, and what (if anything) was to the good

sootyempiric.blogspot.com/2025/08/woke...

Thank you! 🫶🏻