The paper is near submission and you want to stress-test it against the referees it will draw
You need to decide which robustness checks to run before submitting vs. hold in reserve
An R&R arrived and you must map referee concerns to concrete responses
You want to understand how AEJ: Applied's single-blind peer-review process shapes strategy
How AEJ: Applied review works (plan around it)
AEJ: Applied uses single-blind review through the AEA ScholarOne system: author identities are visible to referees, while referee identities remain anonymous to authors. An editor assigns the paper to a coeditor or handles it directly, and before a first R&R the handling coeditor consults a second coeditor. Referees here are identification-literate applied microeconomists; the modal report attacks the credibility of the design first, then magnitude/mechanism, then external validity. The editor weighs whether the contribution is novel and the design clears the bar. Plan to pre-empt the predictable objections in the paper itself, leaving the response letter for genuinely new asks.
The objection map (pre-empt in the paper)
Referee objection (by design)
Pre-emption to build in now
"TWFE is biased under staggered timing"
heterogeneity-robust estimator + Bacon decomposition already in the paper
a test that distinguishes the proposed channel from rivals
"Not reproducible"
the openICPSR package built and referenced (aeja-replication-package)
Strategy craft
War-game the design. For each identifying assumption, write the sentence a hostile referee would use; if you cannot answer it in one paragraph + one exhibit, that is a hole to fix before submission.
Pre-empt, do not hide. Address the obvious weakness head-on in the text; referees punish papers that ignore the elephant.
Sequence robustness. Put decisive checks in the main paper; hold secondary ones for the appendix/online appendix so the paper stays readable.
Anticipate the external-validity ask. It is almost guaranteed for a local design — have the estimand and scope statement ready.
Make reproducibility visible. A referee who sees a clean package is less inclined to suspect specification search.
The shared, venue-neutral objection catalog is in ../../resources/README.md (links to the empirical-methods hub) — walk it before drafting.
Checklist
Title/byline/front matter align with AEJ: Applied's single-blind process
Each identifying assumption has a written hostile-referee sentence and a one-paragraph+one-exhibit answer
The paper's biggest weakness is addressed in the text, not hidden
Decisive robustness in the main paper; secondary checks in the appendix
Estimand + external-validity scope stated to pre-empt the guaranteed ask
Reproducibility package referenced so specification-search suspicion is defused
Mechanism evidence distinguishes the proposed channel from rivals
Anti-patterns
Ignoring the obvious design weakness and hoping no referee notices
Writing self-citations or acknowledgments as if the venue required anonymous review
Dumping every robustness check into the main text so the paper becomes unreadable
No estimand statement, guaranteeing an external-validity round-trip
Treating the replication package as someone else's problem until acceptance
1---2name: aeja-referee-strategy3description: Referee Strategy (aeja-referee-strategy)4---56# Referee Strategy (aeja-referee-strategy)78## When to trigger910- The paper is near submission and you want to stress-test it against the referees it will draw11- You need to decide which robustness checks to run *before* submitting vs. hold in reserve12- An R&R arrived and you must map referee concerns to concrete responses13- You want to understand how AEJ: Applied's single-blind peer-review process shapes strategy1415## How AEJ: Applied review works (plan around it)1617AEJ: Applied uses **single-blind review** through the AEA ScholarOne system: author identities are visible to referees, while referee identities remain anonymous to authors. An editor assigns the paper to a coeditor or handles it directly, and before a first R&R the handling coeditor consults a second coeditor. Referees here are **identification-literate applied microeconomists**; the modal report attacks the *credibility of the design* first, then magnitude/mechanism, then external validity. The editor weighs whether the contribution is novel *and* the design clears the bar. Plan to **pre-empt the predictable objections in the paper itself**, leaving the response letter for genuinely new asks.1819## The objection map (pre-empt in the paper)2021| Referee objection (by design) | Pre-emption to build in now |22|-------------------------------|-----------------------------|23| "TWFE is biased under staggered timing" | heterogeneity-robust estimator + Bacon decomposition already in the paper |24| "Parallel trends is not credible" | clean pre-trend leads + honest-DID sensitivity bound |25| "Instrument is not excludable" | institutional + theoretical exclusion argument + falsification tests |26| "RD jump is manipulation / bandwidth-driven" | density test + bandwidth sensitivity + donut |27| "Effect is just selection / confounding" | Oster δ / coefficient-stability bounds |28| "Local/ITT effect ≠ the policy-relevant effect" | explicit estimand + calibrated external-validity discussion |29| "Inference too narrow (few clusters)" | wild-cluster bootstrap / randomization inference |30| "Mechanism is a black box" | a test that distinguishes the proposed channel from rivals |31| "Not reproducible" | the openICPSR package built and referenced (`aeja-replication-package`) |3233## Strategy craft34351. **War-game the design.** For each identifying assumption, write the sentence a hostile referee would use; if you cannot answer it in one paragraph + one exhibit, that is a hole to fix before submission.362. **Pre-empt, do not hide.** Address the obvious weakness head-on in the text; referees punish papers that ignore the elephant.373. **Sequence robustness.** Put decisive checks in the main paper; hold secondary ones for the appendix/online appendix so the paper stays readable.384. **Anticipate the external-validity ask.** It is almost guaranteed for a local design — have the estimand and scope statement ready.395. **Make reproducibility visible.** A referee who sees a clean package is less inclined to suspect specification search.4041> The shared, venue-neutral objection catalog is in [`../../resources/README.md`](../../resources/README.md) (links to the empirical-methods hub) — walk it before drafting.4243## Checklist4445- [ ] Title/byline/front matter align with AEJ: Applied's single-blind process46- [ ] Each identifying assumption has a written hostile-referee sentence and a one-paragraph+one-exhibit answer47- [ ] The paper's biggest weakness is addressed in the text, not hidden48- [ ] Decisive robustness in the main paper; secondary checks in the appendix49- [ ] Estimand + external-validity scope stated to pre-empt the guaranteed ask50- [ ] Reproducibility package referenced so specification-search suspicion is defused51- [ ] Mechanism evidence distinguishes the proposed channel from rivals5253## Anti-patterns5455- Ignoring the obvious design weakness and hoping no referee notices56- Writing self-citations or acknowledgments as if the venue required anonymous review57- Dumping every robustness check into the main text so the paper becomes unreadable58- No estimand statement, guaranteeing an external-validity round-trip59- Treating the replication package as someone else's problem until acceptance6061## Output format6263```64【Front matter】single-blind title/byline and disclosures ready? [Y/N]65【Objection map】per assumption: [objection → pre-emption in paper]66【Biggest weakness】addressed in text? [Y/N] — how: ___67【Robustness placement】main vs appendix split: ___68【External validity】estimand + scope stated? [Y/N]69【Reproducibility visible】package referenced? [Y/N]70【Next step】aeja-submission71```
Run npx skillmds@latest add gabrielmoreira/aeja-referee-strategy in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.
Referee Strategy (aeja-referee-strategy) It is listed under Coding & Dev Tools on SkillMD.
This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. Capability flags: docs only. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.
This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.
Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.
gabrielmoreira (@gabrielmoreira) published this skill. Their other Agent Skills are listed on their SkillMD profile.