Back to Details

research-ideation

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Research Ideation

研究思路生成

Generate structured research questions, testable hypotheses, and empirical strategies from a topic, phenomenon, or dataset.
Input: 
$ARGUMENTS
— a topic (e.g., "minimum wage effects on employment"), a phenomenon (e.g., "why do firms cluster geographically?"), or a dataset description (e.g., "panel of US counties with pollution and health outcomes, 2000-2020").
根据主题、现象或数据集生成结构化研究问题、可检验假设及实证研究策略。
输入： 
$ARGUMENTS
— 一个主题（例如：“最低工资对就业的影响”）、一种现象（例如：“企业为何会在地理上聚集？”），或一份数据集描述（例如：“2000-2020年美国各县污染与健康结果的面板数据”）。

Steps

步骤

  1. Understand the input. Read 
    $ARGUMENTS
    and any referenced files. Check 
    master_supporting_docs/
    for related papers. Check 
    .claude/rules/
    for domain conventions.
  2. Generate 3-5 research questions ordered from descriptive to causal:
    • Descriptive: What are the patterns? (e.g., "How has X evolved over time?")
    • Correlational: What factors are associated? (e.g., "Is X correlated with Y after controlling for Z?")
    • Causal: What is the effect? (e.g., "What is the causal effect of X on Y?")
    • Mechanism: Why does the effect exist? (e.g., "Through what channel does X affect Y?")
    • Policy: What are the implications? (e.g., "Would policy X improve outcome Y?")
  3. For each research question, develop:
    • Hypothesis: A testable prediction with expected sign/magnitude
    • Identification strategy: How to establish causality (DiD, IV, RDD, synthetic control, etc.)
    • Data requirements: What data would be needed? Is it available?
    • Key assumptions: What must hold for the strategy to be valid?
    • Potential pitfalls: Common threats to identification
    • Related literature: 2-3 papers using similar approaches
  4. Rank the questions by feasibility and contribution.
  5. Save the output to 
    quality_reports/research_ideation_[sanitized_topic].md
  1. 理解输入内容。阅读
    $ARGUMENTS
    及所有参考文件。查看
    master_supporting_docs/
    目录下的相关论文。查看
    .claude/rules/
    目录下的领域规范。
  2. 生成3-5个研究问题，按从描述性到因果性排序：
    • 描述性： 存在哪些模式？（例如：“X随时间如何演变？”）
    • 相关性： 哪些因素存在关联？（例如：“控制Z变量后，X与Y是否相关？”）
    • 因果性： 效应是什么？（例如：“X对Y的因果效应是什么？”）
    • 机制性： 效应为何存在？（例如：“X通过何种渠道影响Y？”）
    • 政策性： 有哪些影响？（例如：“政策X是否会改善结果Y？”）
  3. 针对每个研究问题，开发以下内容：
    • 假设： 带有预期符号/量级的可检验预测
    • 识别策略： 如何确立因果关系（DiD、IV、RDD、合成控制法等）
    • 数据需求： 需要哪些数据？是否可获取？
    • 关键假设： 策略有效必须满足哪些条件？
    • 潜在陷阱： 常见的识别威胁
    • 相关文献： 2-3篇采用类似方法的论文
  4. 按可行性和贡献度对问题排序。
  5. 保存输出内容至
    quality_reports/research_ideation_[sanitized_topic].md

Output Format

输出格式

markdown
undefined
markdown
undefined

Research Ideation: [Topic]

研究思路生成：[主题]

Date: [YYYY-MM-DD] Input: [Original input]
日期： [YYYY-MM-DD] 输入： [原始输入内容]

Overview

概述

[1-2 paragraphs situating the topic and why it matters]
[1-2段话介绍主题背景及其重要性]

Research Questions

研究问题

RQ1: [Question] (Feasibility: High/Medium/Low)

RQ1: [问题] (可行性：高/中/低)

Type: Descriptive / Correlational / Causal / Mechanism / Policy
Hypothesis: [Testable prediction]
Identification Strategy:
  • Method: [e.g., Difference-in-Differences]
  • Treatment: [What varies and when]
  • Control group: [Comparison units]
  • Key assumption: [e.g., Parallel trends]
Data Requirements:
  • [Dataset 1 — what it provides]
  • [Dataset 2 — what it provides]
Potential Pitfalls:
  1. [Threat 1 and possible mitigation]
  2. [Threat 2 and possible mitigation]
Related Work: [Author (Year)], [Author (Year)]
[Repeat for RQ2-RQ5]
类型： 描述性 / 相关性 / 因果性 / 机制性 / 政策性
假设： [可检验预测]
识别策略：
  • 方法： [例如：双重差分法（Difference-in-Differences）]
  • 处理组： [变量的变化及时间节点]
  • 控制组： [对比单元]
  • 关键假设： [例如：平行趋势]
数据需求：
  • [数据集1 — 提供的内容]
  • [数据集2 — 提供的内容]
潜在陷阱：
  1. [威胁1及可能的缓解措施]
  2. [威胁2及可能的缓解措施]
相关研究： [作者（年份）], [作者（年份）]
[重复RQ2-RQ5的内容]

Ranking

排序

RQFeasibilityContributionPriority
1HighMedium...
2MediumHigh...
研究问题可行性贡献度优先级
1高中...
2中高...

Suggested Next Steps

建议下一步行动

  1. [Most promising direction and immediate action]
  2. [Data to obtain]
  3. [Literature to review deeper]

---
  1. [最具前景的方向及即时行动]
  2. [需获取的数据]
  3. [需深入研读的文献]

---

Principles

原则

  • Be creative but grounded. Push beyond obvious questions, but every suggestion must be empirically feasible.
  • Think like a referee. For each causal question, immediately identify the identification challenge.
  • Consider data availability. A brilliant question with no available data is not actionable.
  • Suggest specific datasets where possible (FRED, Census, PSID, administrative data, etc.).
  • 富有创意但立足实际。跳出常规问题的局限，但所有建议必须具备实证可行性。
  • 以审稿人的视角思考。针对每个因果性问题，立即识别出识别挑战。
  • 考虑数据可获取性。一个绝妙但无可用数据支撑的问题不具备可操作性。
  • 尽可能建议具体数据集（如FRED、人口普查数据、PSID、行政数据等）。