Annie H. Lin

I made a public guide for preparing social science replication packages 📦 It includes prompts for Codex/Claude Code 🤖 yhoriuchi.github.io/replication-pa… Please repost if this might help researchers preparing replication materials.

🧵**Structural Conjoint** New paper with Avidit Acharya and Jens Hainmueller: “Learning Preferences from Conjoint Data: A Structural Deep Learning Approach.” We show how to recover interpretable structural parameters from conjoint experiments, combining a random utility model with double-debiased machine learning (DML). Paper: bit.ly/sconjoint

🤖 Can LLMs replicate expert text coding? ➡️ Using interest group documents, @dchoiresearch @DenisPeskoff & @b_m_stewart show that fine tuned LLMs outperform trained coders and zero shot models in identifying informative vs associative signals cambridge.org/core/journals/… #FirstView

⚡ Can political signals push capital toward clean energy? ➡️ P. Bayer @lorenzocrippa & @fgenovese__ show that clear EU Commission announcements during the early Ukraine war briefly moved markets toward greener energy firms cambridge.org/core/journals/… #FirstView

New software: "Projoint: The One Stop Conjoint Stop" (with @aaronrkaufman & @YusakuHoriuchi), makes conjoint surveys easier & less biased, including everything from a drag-and-drop web survey design tool to specialized analysis software. Comments welcome. yhoriuchi.github.io/projoint/

We are pleased to announce the 2025 Editors’ Choice Award for the paper “How Much Should We Trust Instrumental Variable Estimates in Political Science? Practical Advice Based on 67 Replicated Studies” by @Apoorva__Lal, @lockhartm, @xuyiqing, and @zu_gary.

#RDDers: check it out. Difference-in-Discontinuities: Estimation, Inference, and Validity Tests.

Exit from International Organizations by Inken von Borzyskowski and Felicity Vabulas A theoretically grounded and empirically systematic study of exit from international organizations across 198 states, 534 IOs, and 100 years. 📚 cup.org/3TXhgas

Difference-in-differences for practitioners from the diff-in-diffs dream team!

Glad this paper is finally out in @apsrjournal, five years after we began the project. Hope it proves useful to researchers. cambridge.org/core/journals/…

RIP.

New Publication Alert: "Innovation and Interdependence: Evidence from Gene-Editing Technology" is now out in @ISQ_Jrnl. Check out this cool paper. doi.org/10.1093/isq/sq…

Currently in FirstView: “Synthetically generated text for supervised text analysis.” @ahalterman proposes a method for using LLMs to generate synthetic training data for training smaller, traditional supervised text models.

📊Structural equation modeling is common in political science, but model specification is tricky. ➡️B.Q. Zheng & P.M. Bentler propose a stepwise bootstrapped LM test to better detect missing parameters—improving fit, especially in small samples cambridge.org/core/journals/… #FirstView

Looking for new ways to access and work with Global Fishing Watch data? Our official Python API package is here - get AIS fishing effort, SAR vessel detections, vessel behavior & more in just a few lines of code. Learn more 👉 globalfishingwatch.org/platform-updat…

Slides for my talk at UCF on "Correcting Measurement Error Bias in Conjoint Survey Experiments" (now forthcoming in the AJPS; GaryKing.org/conjointE) along with work on Survey Instability: gking.harvard.edu/presentations/… Thanks to everyone at UCF for a great visit!

Just published on APSR First View: "Domestic Institutions, Geographic Concentration, and Agricultural Liberalization" by In Song Kim, Megumi Naoi, and Tomoya Sasaki. cambridge.org/core/journals/…

#OpenAccess from @apsrjournal - Why Was the American Revolution a War? A Rationalist Interpretation - cup.org/4ietzcS - DAVID A. LAKE (@UCSanDiego) #FirstView

New work on legitimacy and IOs by Thomas Sommerer and @JonasTallberg published in the @The_JOP. Full article here: doi.org/10.1086/735474

A framework for analyzing how institutions, market structures, and technological choices affect societal resource distribution and development across different historical periods, from colonialism to modern AI, from @DrDaronAcemoglu nber.org/papers/w33442