Agent skill · Business & Finance

cte-identification

Use when the empirical identification strategy is the bottleneck for a 《财贸经济》 manuscript — fiscal / tax / financial / trade policy shocks and firm- / city- / bank-level quasi-experimental designs (DID, IV, RDD, DML). Stress-tests the design and the policy endogeneity before drafting tables. 本技能服务于《财贸经济》(Finance & Trade Economics, CTE)。

brycew6m878★ · +32/wk · 1 repos on radarProfile →
claude-codeMIT
Install
npx skills add brycewang-stanford/Awesome-Journal-Skills --skill cte-identification --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: Finance-and-Trade-Economics-Skills/skills/cte-identification/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

# 因果识别策略(cte-identification) ## 触发时机 - 实证主体仅有描述统计 + OLS + 控制变量 - 核心解释变量是**政策 / 制度冲击**(税制改革、财政试点、金融监管、贸易政策),但没处理政策内生与预期 - DID 用了 TWFE 但没回应近年异质性处理批评(Goodman-Bacon, de Chaisemartin, Sun-Abraham, Callaway-Sant'Anna) - IV 第一阶段 F 弱 / 工具变量排他性疑虑 - 用了机器学习控制高维协变量但没做正交化 / 交叉拟合(DML) ## 设计优先级 《财贸经济》编委对财经实证的偏好排序(强 → 弱): 1. **财经政策冲击 + DID(含 staggered / continuous treatment)**——如营改增、减税降费、财政试点、金融监管改革、自贸区 / 关税调整的分批推行 2. **断点回归 / 断点**——清晰的政策门槛(如税收优惠资格线、财政转移支付分档线、监管资本门槛、贫困县 / 城市规模分档) 3. **工具变量**——强工具 + 排他性论证(处理政策内生与反向因果的核心武器) 4. **双重机器学习(DML)**——高维协变量 / 非线性混淆下的稳健处理效应估计 5. **合成控制法**——城市 / 省级政策评估(如单一试点城市) 6. OLS + 严密的内生性讨论(仅在有强外生性论证或结构 / 理论实证时可接受) ## 财经数据的内生性专项 财经实证最常见的内生性来源,审稿人必查: - **政策内生**:政策是否非随机地投向"本就更好 / 更差"的地区 / 企业(如试点先选基础好的城市)? - **反向因果**:是先有金融风险才有监管,还是监管带来风险变化? - **预期效应**:市场主体是否在政策正式落地前已提前调整(抢出口、突击减税前投资)? - **测量与口径**:财税口径 / 会计科目 / 贸易统计的可比性与操纵空间 针对性策略至少给出一条:固定效应 + 准实验冲击 / IV / 断点 / DML;纯 Heckman 或纯 PSM 仅作辅助,不能单独立住识别。 ## 分支路径 ### 分支 A:DID - 是否 staggered?→ 必须用 Goodman-Bacon 分解 + Callaway-Sant'Anna 或 Sun-Abraham - 平行趋势检验:事件研究图必须画,处理时点前系数应不显著 - 安慰剂:随机分配处理组 / 处理时点 500–1000 次 - 连续处理(如税率变动幅度)需回应剂量-反应的异质性偏误 ### 分支 B:IV - 第一阶段 F **必须 ≥ 10**(弱工具 → 用 Anderson-Rubin 或 weak-IV-robust CI) - 排他性论证至少 3 段:理论 / 制

What's inside
Steps it walks through
  1. 触发时机
  2. 设计优先级
  3. 财经数据的内生性专项
  4. 分支路径
  5. 分支 A:DID
  6. 分支 B:IV
  7. 分支 C:RDD / 断点
  8. 分支 D:DML / 双重机器学习
  9. 分支 E:结构估计 / 理论实证
  10. Execution bridge (StatsPAI / Stata MCP)
  11. 必查清单
  12. 反模式
  13. 输出格式
More from Awesome-Journal-Skills
All skills →
About this skill
What does the cte-identification skill do?

Use when the empirical identification strategy is the bottleneck for a 《财贸经济》 manuscript — fiscal / tax / financial / trade policy shocks and firm- / city- / bank-level quasi-experimental designs (DID, IV, RDD, DML). Stress-tests the design and the policy endogeneity before drafting tables. 本技能服务于《财贸经济》(Finance & Trade Economics, CTE)。

How do I install it?

Run `npx skills add brycewang-stanford/Awesome-Journal-Skills --skill cte-identification --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