科研 Skill

质性编码与主题分析

alterlab-qualitative-analysis

Builds codebooks and computes intercoder reliability (Krippendorff’s alpha, kappa) for thematic or content coding, including human-vs-LLM double coding. Use when coding text or reporting reliability.

发布者 Codar安全审核通过v0.1.0更新于 2026-11-18

SKILL.md

Qualitative Analysis — Reliability When It Fits, Consensus When It Doesn't

Skill type: ANALYSIS MODULE. Codes qualitative data and reports agreement correctly. The central discipline is a branch: a reliability coefficient is right for codebook/content-analytic work, but for reflexive thematic analysis the criterion is consensus and reflexivity, not a statistic. The skill does not oversell the number.

Core Mission

KRIPPENDORFF'S ALPHA IS THE PRIMARY COEFFICIENT — BUT A COEFFICIENT IS THE WRONG TOOL FOR REFLEXIVE TA.
BRANCH BY DESIGN.

When to Use This Skill

  • "Two RAs coded my interviews with a codebook — compute intercoder reliability."
  • "Build/refine a codebook and report agreement."
  • "I used an LLM to code open-ended responses — does it agree with my human coding?"
  • "Which reliability statistics do I report for a content analysis?"

Does NOT Trigger

The request is really about…Route toWhy not this skill
Topic modeling / embeddings / supervised text classificationalterlab-text-as-dataComputational text, not human-coding reliability.
Whether the study is trustworthy (positionality, Lincoln & Guba)alterlab-ssci-reflexivity-gateTrustworthiness gate, not the coding itself.
Choosing the qualitative method (grounded theory, phenomenology)alterlab-qualitative-methodsMethodology selection, upstream.
Whether a scale is reliable/valid (quantitative)alterlab-ssci-measurement-gatePsychometrics, different problem.

Hand-off rule. When the request matches a row above, open your answer by naming that skill by its exact id (for example alterlab-text-as-data) and saying in one line why it fits better, then stop applying this skill's procedure. Name it even when you also need to ask for missing input. If only part of the request is out of scope, name the skill for that part and do only the in-scope part. A brief general pointer is fine; the named skill does the work.

Running the code. In Claude Code, run analysis code in a throwaway environment instead of installing packages: python scripts/icr.py coding.csv (stdlib, nominal codes) or uv run --python ">=3.11" --with "krippendorff>=0.8" --with pandas python icr.py. This needs no install approval and leaves the user's environment untouched. If uv or the network is unavailable, say so and hand over the script; never report results you did not compute.

The branch (this is the core discipline)

DesignReliability criterion
Codebook / content-analytic coding (fixed categories, replicable)compute an ICR coefficient (Krippendorff's α) with a CI and threshold
Reflexive thematic analysis (interpretive, researcher-as-instrument)consensus + reflexivity — collaborative discussion to understand differences; a coefficient misrepresents the epistemology and is NOT required. Route trustworthiness to alterlab-ssci-reflexivity-gate.

Do not force α onto reflexive TA, and do not skip α on content-analytic coding.

Correct coefficient choice (verified)

  • Krippendorff's α — primary. Handles ≥2 coders, any measurement level (nominal/ordinal/ interval/ratio), and missing data. Python krippendorff.alpha(reliability_data=<coders × units>, level_of_measurement="nominal") returns a point estimate only — pair it with a bootstrap CI (the bundled scripts/icr.py does nominal α + a bootstrap CI + Cohen's κ in pure stdlib; R irrCAC::krippen.alpha.raw or icr::krippalpha(..., bootstrap=TRUE) give CIs for all levels).
  • Cohen's κ (2 coders) / Fleiss' κ (>2, fixed number): statsmodels.stats.inter_rater cohens_kappa, fleiss_kappa (build the count table with aggregate_raters); sklearn cohen_kappa_score as a cross-check.
  • NOT valid ICR measures: chi-square, Cronbach's alpha, and Pearson's r — they measure covariation/internal consistency, not chance-corrected agreement. Refuse these.

Thresholds (Krippendorff): α ≥ .80 reliable; .667 ≤ α < .80 tentative conclusions only; α < .667 unreliable. Report α with a 95% CI, never the bare point estimate.

LLM-assisted coding (supported, never free)

Treat an LLM as another coder: human↔LLM double-coding, compute Krippendorff's α between each LLM and a human gold standard, and use the CI to judge whether the LLM is statistically indistinguishable from human coders. Disclose the model, the prompt, and the agreement — never present LLM coding as uncontrolled or cost-free.

Reporting checklist (put in every ICR report)

BRANCH:        content-analytic (coefficient) | reflexive TA (consensus+reflexivity)
ICR MEASURE:   Krippendorff alpha (level) | Cohen/Fleiss kappa — and why
CODERS:        number of coders; human / LLM
DOUBLE-CODED:  % of the data double-coded
ALPHA:         point estimate + 95% CI + threshold verdict (.80 / .667)
RESOLUTION:    how disagreements were resolved (adjudication / consensus)

References

  • references/icr_and_reporting.md — coefficient math, verified APIs, LLM-benchmarking, the reporting standard.
  • references/reflexive_vs_codebook.md — when a statistic applies vs. when it does not.
  • scripts/icr.py — stdlib nominal Krippendorff's α + bootstrap CI + Cohen's κ (no numpy / no deps). CSV: a header of ≥ 2 coder names, one row per unit, exactly one cell per coder (blank = missing). α and κ are reported as not estimable when every pairable code is one category.

Part of the AlterLab Academic Skills suite.

示例提示词

帮我对访谈逐字稿做主题编码,并计算编码者间信度。

所属插件

社会学、政治学与城市研究面向社会科学研究:问卷与访谈设计、质性编码、文本即数据、社会网络、ABM、比较政治与选举数据、RCT 与 DID、城市与区域分析。

安装该插件会一并获得同领域的 58 个 Skill / MCP。

同插件的其他科研 Skill

常见问题

质性编码与主题分析能做什么?

Builds codebooks and computes intercoder reliability (Krippendorff’s alpha, kappa) for thematic or content coding, including human-vs-LLM double coding. Use when coding text or reporting reliability。

如何安装质性编码与主题分析?

在科搭 Codar 左侧点击「插件」,在「组件」页签搜索「质性编码与主题分析」并安装;在 Claude Code 或 Codex 中可以发送本页的安装提示词,或下载 Skill 包后解压到 ~/.claude/skills 或 ~/.codex/skills。

质性编码与主题分析需要哪些权限?

该科研 Skill没有声明额外权限;执行具体操作时仍由 Agent 按自身规则请求确认。

质性编码与主题分析经过官方审核吗?

是。SpeedSkills 收录的每个版本都会记录内容摘要与权限声明,当前版本已通过安全审核。