Agent skill · Code Review & Quality

nbr-experiment

Use for experimental studies submitted to 《南开管理评论》 (Nankai Business Review) — design (between/within, scenario/vignette, lab/field), manipulation checks, randomization and confound control, effect sizes and power, and mediation/moderation via experimental-causal-chain or measurement-of-mediation designs. Use when a hypothesis is tested by manipulating an independent variable rather than measuring it.

brycew6m878★ · +32/wk · 1 repos on radarProfile →
claude-codeMIT
Install
npx skills add brycewang-stanford/Awesome-Journal-Skills --skill nbr-experiment --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: Nankai-Business-Review-Skills/skills/nbr-experiment/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

# 实验法(nbr-experiment) ## 触发时机 - 自变量是**操纵**出来的(情境/启动/任务),不是测量 - 用情境实验(vignette/scenario)、实验室或现场实验做因果推断 - 想用实验补强问卷研究的内部效度(多研究设计) ## 设计要点 - 明确**被试间 / 被试内 / 混合**设计,给出各组样本量与分配 - 操纵材料**预测试(pilot)**:确认操纵有效、强度适中、无混淆 - **随机分配**到条件,报告分配方式;现场实验交代随机化层级 ## 设计选型速查 | 设计 | 适用 | 本刊注意点 | |------|------|-----------| | 情境/卷面实验(vignette) | 操纵感知类构念(领导风格、算法反馈) | 材料须本土化改写并预测试,防"翻译腔"折损真实感 | | 实验室实验 | 行为因变量(合作、投入、选择) | 报告被试来源(学生/在职),讨论可推广性 | | 现场实验 | 组织内真实干预 | 交代随机化层级与企业配合细节;在本刊稀缺但竞争力强 | ## 走查示例:AI 反馈与员工创意 设想 2(反馈来源:AI / 主管)× 2(效价:肯定 / 否定)被试间情境实验,因变量为创意任务表现: 1. 预测试 60 人确认 AI/主管操纵的感知差异显著、材料真实感均值过线(如 7 点量表 > 5) 2. 正式实验各组 n ≥ 50,随机分配由平台自动完成并在文中报告 3. 操纵检验:来源感知主效应显著,且不影响"反馈具体性"评分(排除混淆) 4. 结果报告 η²p 与功效;交互显著后做简单效应分解 5. 研究 2 直接操纵中介(自我效能高/低启动)构成实验因果链——比只测中介更能说服本刊审稿人 ## 多研究组合策略 本刊组织行为与营销类稿件常以"问卷 + 实验"双研究互补:问卷立外部效度,实验补内部效度。组合时让两个研究共用同一条机制链,不要各测各的;两研究在样本与情境上的差异,应在讨论中作为稳健性证据陈述。若实验先行(研究 1),可用企业在职样本问卷(研究 2)检验机制在真实组织中的再现,顺序由理论成熟度决定。 ## 操纵检验与混淆控制 - **操纵检验(manipulation check)**:证明操纵确实改变了目标构念,且**未同时改变**其它构念 - **混淆排查**:需求特征、注意力检验(attention check)、可信度/真实感评分 - 报告**剔除标准**(未通过注意力/操纵检验者)及剔除前后稳健性 ## 统计与效应量 - 报告**效应量**(Cohen's d / η²p / f),不只报 p 值 - 交代**功效分析(power)**或样本量依据 - 多重比较做校正;必要时报告贝叶斯因子或等效性检验 - **机制**:用**实验因果链**(操纵中介变量)或**测量中介

What's inside
Steps it walks through
  1. 触发时机
  2. 设计要点
  3. 设计选型速查
  4. 走查示例:AI 反馈与员工创意
  5. 多研究组合策略
  6. 操纵检验与混淆控制
  7. 统计与效应量
  8. 执行桥(StatsPAI / Stata MCP)
  9. 自检清单
  10. 反模式
  11. 评审质疑与补救
  12. 输出格式
More from Awesome-Journal-Skills
All skills →
About this skill
What does the nbr-experiment skill do?

Use for experimental studies submitted to 《南开管理评论》 (Nankai Business Review) — design (between/within, scenario/vignette, lab/field), manipulation checks, randomization and confound control, effect sizes and power, and mediation/moderation via experimental-causal-chain or measurement-of-mediation designs. Use when a hypothesis is tested by manipulating an independent variable rather than measuring it.

How do I install it?

Run `npx skills add brycewang-stanford/Awesome-Journal-Skills --skill nbr-experiment --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