Agent skill

ceq-modern-did

Use when a 《经济学(季刊)》 (China Economic Quarterly, CEQ) manuscript uses difference-in-differences with staggered adoption or heterogeneous treatment effects — to bring it into compliance with modern estimators (Callaway–Sant'Anna, de Chaisemartin–D'Haultfœuille, Sun–Abraham) instead of bare two-way fixed effects. Bare TWFE on staggered timing is a near-certain reject at CEQ.

brycew6m4,252★ · +31/wk · 3 repos on radarProfile →
claude-codeMIT
Install
npx skills add brycewang-stanford/Awesome-Journal-Skills --skill ceq-modern-did --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 1
SKILL.md size: 3 KB
Bundled scripts: none
Path: China-Economic-Quarterly-Skills/skills/ceq-modern-did/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 909 · +31 this week
Language: Stata
Read our review of the source →

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# 现代 DID 合规(ceq-modern-did) ## 触发时机 - 处理时点**交错**(不同单位不同时间被处理),但只跑了 TWFE - 处理效应可能随队列/时间**异质** - 审稿人提"负权重 / 坏比较 / 前置效应"等批评 ## 核心判断:你的 DID 是哪一类? | 情形 | 是否有 TWFE 偏误 | 处理 | |------|------------------|------| | 单一时点、两组 | 通常无 | 标准 DID 即可,仍画事件研究图 | | 交错处理 + 同质效应 | 轻 | 仍建议稳健估计量交叉验证 | | 交错处理 + 异质效应 | **严重(负权重)** | **必须**用现代估计量 | | 连续/强度处理 | 视情形 | 用 de Chaisemartin–D'Haultfœuille 等专用估计量 | ## 必做四步(交错处理) 1. **诊断**:Goodman-Bacon 分解,报告"坏比较"(already-treated 作对照)的权重;或 de Chaisemartin–D'Haultfœuille 负权重诊断。 2. **现代估计量**(至少一种,建议交叉验证两种): - Callaway–Sant'Anna(`csdid` / `did`):分组-时间 ATT 聚合 - de Chaisemartin–D'Haultfœuille(`did_multiplegt(dyn)`):适配连续/可逆处理 - Sun–Abraham(`eventstudyinteract`):交互加权事件研究 3. **事件研究图**:用上述估计量画动态效应(见 `ceq-figures`),而非 TWFE 的污染系数。 4. **对照报告**:TWFE 与现代估计量并列,说明差异来源。 ## 易踩坑 - 用 TWFE 事件研究图当"平行趋势成立"——其前置系数本身被污染 - 把 not-yet-treated 与 already-treated 混作对照而不说明 - 连续处理直接套 Callaway–Sant'Anna(其默认针对二元吸收处理) - 只报现代估计量的点估计,不报其聚合方式与对照组定义 ## 自检清单 - [ ] 已诊断是否交错 + 是否异质(决定要不要现代估计量) - [ ] 至少一种现代估计量;建议两种交叉验证 - [ ] 事件研究图来自现代估计量,前置系数近零 - [ ] 报告了对照组定义(never/not-yet-treated)与聚合权重 - [ ] TWFE 与现代估计量并列,差异有解释 - [ ] 连续/可逆处理用了适配的估计量 ## 反模式 - 裸 TWFE 跑交错处理直接声称因果(CEQ 退稿高发) - 不做负权重/坏比较诊断 - "我们也跑了 Callaway-Sant'Anna,结

What's inside
Steps it walks through
  1. 触发时机
  2. 核心判断:你的 DID 是哪一类?
  3. 必做四步(交错处理)
  4. 易踩坑
  5. 自检清单
  6. 反模式
  7. 现代 DID 合规对照表(症状→估计量→必报项)
  8. 微型走查:TWFE 与现代估计量并列
  9. 审稿人追问模式与修法
  10. 输出格式
More from Awesome-Journal-Skills
All skills →
About this skill
What does the ceq-modern-did skill do?

Use when a 《经济学(季刊)》 (China Economic Quarterly, CEQ) manuscript uses difference-in-differences with staggered adoption or heterogeneous treatment effects — to bring it into compliance with modern estimators (Callaway–Sant'Anna, de Chaisemartin–D'Haultfœuille, Sun–Abraham) instead of bare two-way fixed effects. Bare TWFE on staggered timing is a near-certain reject at CEQ.

How do I install it?

Run `npx skills add brycewang-stanford/Awesome-Journal-Skills --skill ceq-modern-did --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From brycewang-stanford/Awesome-Journal-Skills, a repository with 909 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going