From restat-skills
Stress-tests causal identification and measurement strategy for REStat manuscripts (DID, RD, IV, shift-share, measurement-error problems).
How this skill is triggered — by the user, by Claude, or both
Slash command
/restat-skills:restat-identificationThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
- A causal claim rests on OLS + controls, or TWFE on staggered timing
REStat is applied econometrics with a measurement tradition, so two things are judged together: the mapping from data to the causal object must be explicit and defended, and the quality of measurement behind every variable must be credible. A clean design on a badly measured construct does not clear the bar; neither does a beautifully measured variable in a hopelessly confounded regression. Report standard errors and modern inference; clustering at the assignment level; address attenuation and other measurement-error biases head-on — REStat referees raise measurement objections sibling journals sometimes wave through.
A paper regresses earnings on a survey-reported measure of training hours and finds a small effect. A REStat referee notes the training measure is self-reported and likely error-ridden, biasing the coefficient toward zero. The fix: bring an administrative validation subsample, estimate the reliability ratio (say 0.6, illustrative), and show the attenuation-corrected effect is roughly 1/0.6 larger — turning a "small" effect into an economically meaningful one, with the correction's assumptions stated. Measurement, not just identification, moved the answer.
【Branch】DID / RD / IV / shift-share / measurement
【Data-to-object mapping】one sentence
【Identification evidence】[event-study+Bacon / density+smoothness / first-stage+AR / shares-or-shocks]
【Measurement evidence】[construct validity / error correction / bounds] — or "n/a, cleanly measured"
【Inference】SEs + clustering level; few-cluster fix if any
【What it does NOT identify】[...]
【Next step】restat-theory-model (or restat-robustness if theory is minimal)
npx claudepluginhub brycewang-stanford/awesome-journal-skills --plugin restat-skillsGuides selection, implementation, and stress-testing of causal identification strategies for REStud manuscripts: DID, IV, RDD, synthetic control, shift-share, RCT.
Stress-tests causal identification arguments (RCT, DiD, RD, IV, shift-share) for AEJ: Applied manuscripts, ensuring designs meet the journal's credibility bar before exhibits are finalized.
Stress-tests causal identification designs (DiD, IV, RDD, experiment) for EER manuscripts, ensuring credibility before finalizing exhibits.