Compare Research Methods

Compare Research Methods

Discipline And Interview Setup

Read discipline-routing.md, then only the selected discipline profile. Reuse the user's existing brief; do not restart intake at each stage. For journalism/communication or information science, use that profile's concepts, extraction fields, and appraisal checks instead of a generic social-science template.

When the user requests "grill me", 追问, or 模拟答辩, read research-interview.md. Ask one decision-relevant question per turn and wait; do not generate the stage deliverable until enough decisions are settled or the user asks to proceed. In quick/no-question mode, record assumptions and continue without inventing answers.

For evidence extraction or drafting, read review-workflow.md. With no sources, give a plan or outline, not a purported synthesis. If reference files are unavailable, retain the source guardrails below and state that discipline guidance is missing.

Goal

Help the user treat method choice as an argument, not a format requirement. Every recommended method should explain what part of the research question it answers, what it cannot answer, and why it fits better than alternatives.

Workflow

1. Distinguish appraisal of included studies, choice of review method, and design of a future empirical study. Default to appraisal when the user is writing a review; do not silently turn it into a new study proposal.
2. List plausible methods rather than jumping to the user's preferred method.
3. Build a three-column comparison: method route, can answer, cannot answer.
4. Identify the tradeoff that matters most for this question.
5. For appraisal, recommend a synthesis/appraisal approach and state which claims the included designs support. Only propose a new empirical design when requested. Use the selected discipline's checks, including interpretive or historical methods where relevant.

Comparison Table Template

Use this structure:

markdownCopy code
| Method route | Can answer | Cannot answer |
|---|---|---|
| Survey + regression | Which factors are significantly associated with the outcome | How participants actually make decisions or interpret tradeoffs |
| In-depth interviews | Why actors persist, withdraw, or change behavior | Whether the pattern generalizes to a larger population |
| Panel data | Within-unit change over time and conditional associations | Causal attribution without a defensible identification strategy and its assumptions; lived mechanisms without suitable evidence |
| Case comparison | How context shapes mechanisms across cases | Precise population-level effect size |

Adapt the method list to the user's field and data reality.

Rationale Pattern

Write method justification with this chain:

textCopy code
Because prior studies mainly [current limitation], and this question needs to explain [target need], use [method/design] to [specific function]. This method can clarify [answer], but it cannot fully resolve [boundary], so [supplement/limitation statement].

For mixed methods, specify the sequence:

• Quantitative first: use when broad patterns or key variables must be identified before explaining mechanisms.
• Qualitative first: use when concepts, mechanisms, or categories are unclear and need exploration before measurement.
• Parallel design: use when breadth and depth are both needed and can be compared after collection.

Output Format

Provide:

markdownCopy code
## Method Need

[What the research question most needs]

## Method Comparison

| Method route | Can answer | Cannot answer |
|---|---|---|

## Recommended Design

[Appraisal/synthesis approach for a review, or method/sequence for an explicitly requested future study]

## 段落草稿（需作者改写并核对来源）

[Draft paragraph. Start with: "以下为草稿，请改写成你自己的论证，并逐句核对来源后再使用。" Tag every literature-dependent sentence with source and status, or [需补来源]]

## Boundary Statement

[What this design still cannot claim]

## 待核实清单

[Unverified sources, "未查到" results, sentences marked [需补来源], and inferences that still need checking; write "无" if empty]

## 给作者的问题

[Judgment calls that belong to the author; write "无" if empty]

The output sections above, and the two closing sections, keep fixed names and order; see references/output-contract.md (a copy bundled in this skill folder).

Guardrails

• Do not say a method is "best" without naming the question need it satisfies.
• Do not hide limitations; make them part of the justification.
• Do not recommend mixed methods as a default. Use mixed methods only when the question genuinely needs complementary evidence.
• Source integrity: follow references/source-integrity.md. Any statement about what prior studies did must point to a tagged source or be marked [需补来源]. Use only sources the user provided or that are verified, tag each with a status (用户提供 / 已核验 / 未核验), write "未查到" instead of completing authors, year, journal, or pages, and put anything unverified in ## 待核实清单. If that file is not available, still apply these rules.