Fun exercise for students in a causal inference class: draw a DAG for this debate.

Adam Bonica@adambonica.bsky.social · 10mo ago

Look. It would be great if there was one simple trick for winning elections. But 'just be more moderate' isn't it. In fact, you can use the NYT's exact method to 'prove' a 'Progressive Advantage' of +1.4 pts. This piece shows what's really going on: funded candidates do better than unfunded ones.

Interesting response by @yiqingxu.bsky.social and others to @urisohn.bsky.social: arxiv.org/pdf/2502.05717 Causal inference is serious job. In Pearl's parlance, "define first, identify second, estimate last". If the 2 first parts are correct, one can use adaptive models in semiparametric fashion.

A very cool Econometrics Journal editorial by @jaapabbring.bsky.social, @victorchernozhukov.bsky.social & Fernandez-Val on Wright's 1928 contribution to causal inference and IV. Very interesting stuff! Link: arxiv.org/abs/2501.16395

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...

Pedro Sant’Anna@pedrosantanna.bsky.social · 2y ago

I am thinking of making my DiD materials that I used for teaching in the last 5 years available. I am hoping these would find begineers in need of a step-by-step opinionated walkthrough of several developments Let’s see if I find the energy to do this!

I am thrilled to announce that I will be joining Department of Government at Harvard University, first as a postdoctoral fellow (2025) and then as an assistant professor (2026). I am grateful and really excited for this new opportunity.

New paper! arxiv.org/pdf/2411.14285 Led by amazing postdoc Alex Levis: www.awlevis.com/about/ We show causal effects of new "soft" interventions are less sensitive to unmeasured confounding & study which effects are *least* sensitive to confounding -> makes new connections to optimal transport

academic.oup.com/ije/article/... #causalsky #statsky #episky #causalinference

M-estimation for common epidemiological measures: introduction and applied examples

Abstract. M-estimation is a statistical procedure that is particularly advantageous for some comon epidemiological analyses, including approaches to estima

academic.oup.com

#Rstats `MatchIt` v4.6.0 is out! `MatchIt` implements propensity score matching and other matching methods for causal effect estimation. This isn't a major release, but here are the main updates: 🧵 #causalsky #econsky #episky #statsky

I made a starter-pack for Statistics and Statistics-related groups, departments or organisations. Please share, and suggest accounts that I have missed. go.bsky.app/q6MfWL

Econ has some ML gems. One of my favorite's is Sandroni's sweeping result that no empirical test can distinguish an informed from an uninformed forecaster. I teach it in my ML class: www.youtube.com/watch?v=7OAI... But it is presented as negative, when it is in fact a sweeping positive result.

CIS 6200: Learning with Conditional Guarantees, Lecture 21.

YouTube video by Aaron Roth

youtube.com

(brand new, WIP) python package for synthetic control estimators with a fast weight solver (pyensmallen). Currently implements jacknife CIs since inference in single-treated setting is basically made up anyway. hope this passes muster, @paulgp.com ? github.com/apoorvalal/s...

GitHub - apoorvalal/synthlearners: fast synthetic control estimators for panel data problems

fast synthetic control estimators for panel data problems - apoorvalal/synthlearners

github.com

"Recent Developments in Partial Identification" by Kline and Tamer (2023). #stats 📉📈 For those curious about Manski bounds and partial identification more generally, a nice review! Open access: www.annualreviews.org/content/jour...

The only part of Twitter worth preserving are those Wooldridge threads on Poisson QMLE.

🚨GRAVE: usuário do Bluesky cria lista que permite bloquear de uma vez uma penca de perfis caça-clique que espalham fofoca, exagero, inutilidade e desinformação. bsky.app/profile/did:...

I, of course, would never pander to the delightful new community of folks joining Bluesky by pointing out that Brazilian mayoral elections are a major use case for difference-in-differences methods.

Amanda Weiss@amandaweiss.bsky.social · 2y ago

🚨 Job Market Paper alert! "How Much Should We Trust Modern Difference-in-Differences Estimates?" at osf.io/bqmws I assess the fit between modern DID-style estimators and real-world data features, and point to approaches for improving inference. Quick thread ⬇️

A starter pack with causal inference I know. Unsure if this is the correct way of doing this, but I'm learning go.bsky.app/FdemGAZ

Based on this skeet by @stephenjwild.bsky.social , I will start a skeet thread on free resources for causal inference I know. First one is obviously this recent book by Peng Ding. Strengths of this book are the focus on statistical inference (randomization, matching, and sensitivity analysis).

Stephen Wild@stephenjwild.bsky.social · 2y ago

If you want a sneak peak of the whole book: arxiv.org/abs/2305.18793 I prefer physical copies, but I won't hold it against anyone who prefers electronic versions.

Show yourselves causality people. #stats

Guilherme Duarte@guilhermeduarte.bsky.social · 2y ago

Where are the causality people?

Where are the causality people?

Rafael Izbicki@rafael-izbicki.bsky.social · 2y ago

Any stats or machine learning researchers in Blue Sky?

My blog post critical of this re-analysis is up: matthewbjane.com/blog-posts/blo… The re-analysis conducted by Rausch & Haidt does not follow a principled statistical approach. I re-do their re-analysis with appropriate statistical methods

Pra quem ta chegando agora, pf usem o mesmo avatar que tinham na outra rede por enquanto.

X-ilado

A warm welcome to everyone arriving from Brazil. I know you don't have crows or ravens (except for the occasional invasive pied crow) but you have caracaras, which seem to be very similar in behavior and spirit. Maybe some of you even have pictures? Below, a fine raven in San Francisco. 🪶

The seamless interface between estimatr and modelsummary in R is such an efficiency boost, not to mention the brilliant performance of each respective package. @vincentab.bsky.social @aecoppock.bsky.social @graemeblair.bsky.social @macartan.bsky.social bravo and many thanks!

For polisky folks: Job alert: UChicago seeks an Instructional Assistant Professor (Lecturer) to teach undergraduate social science research methods. This is a two-year, renewable teaching position suitable for any social science PhD. Apply below (EOE/Vet/Disability) apply.interfolio.com/134140

This paper was so fun: arxiv.org/pdf/2301.121... We give new methods for estimating bounds on avg treatment effects - trt is confounded, but an instrument is available. Super common in practice The bounds are non-smooth, so std efficiency theory isn't applicable Lots of useful nuggets throughout!

A new paper with Ye Wang and Aaron Zhou that uses random forests to improve Lee (2009) trimming bounds for partial identification under endogenous sample selection: arxiv.org/abs/2309.08985