Apply case study research design (Yin) to investigate how and why questions within real-life contexts using single or multiple case designs and triangulation. Use this skill when the user needs to choose between single and multiple case designs, apply holistic versus embedded units of analysis, triangulate evidence from multiple sources, or when they ask 'how should I structure a case study', 'single or multiple cases', or 'how do I ensure validity in case research'.
Case study research is an empirical inquiry that investigates a contemporary phenomenon in depth and within its real-life context, especially when the boundaries between phenomenon and context are not clearly evident. Yin's framework provides systematic design choices — single vs. multiple cases, holistic vs. embedded analysis — and emphasizes triangulation to strengthen construct validity.
IRON LAW: Case study answers HOW and WHY questions in context — if you
need frequency or incidence data, use a survey or experiment instead.
Applying case study to "how many" or "how much" questions misuses the
methodology.
Key assumptions:
Define the research question (how/why). Select the case type using Yin's 2x2 matrix:
| Single Case | Multiple Case | |
|---|---|---|
| Holistic (single unit) | Critical, unique, or revelatory case | Literal or theoretical replication |
| Embedded (multiple units) | Multiple units within one case | Multiple units across cases |
Develop propositions to guide data collection.
Gather data from at least three of six source types: documents, archival records, interviews, direct observation, participant observation, physical artifacts. Maintain a chain of evidence linking questions to data to conclusions.
| Triangulation Type | Description |
|---|---|
| Data | Multiple data sources converge on the same finding |
| Investigator | Multiple researchers independently analyze the same data |
| Theory | Multiple theoretical perspectives applied to the same data |
| Methodological | Multiple methods (qual + quant) address the same question |
Use pattern matching, explanation building, time-series analysis, or cross-case synthesis. Report the chain of evidence transparently.
## Case Study Analysis: [Context]
### Research Question
- Question: [the how/why question]
- Case type: [single/multiple] x [holistic/embedded]
- Unit of analysis: [what constitutes the "case"]
### Case Selection Rationale
| Case | Rationale | Expected Pattern |
|------|-----------|-----------------|
| [name] | [why selected] | [literal/theoretical replication] |
### Evidence Matrix
| Source Type | Data Collected | Key Findings |
|------------|---------------|--------------|
| [documents/interviews/etc.] | [description] | [finding] |
### Triangulation Results
- Convergent findings: [where sources agree]
- Divergent findings: [where sources disagree]
- Explanation: [how divergence is resolved]
### Pattern Matching
- Predicted pattern: [from propositions]
- Observed pattern: [from evidence]
- Match assessment: [strong/moderate/weak]
### Conclusions
1. [Key finding with chain of evidence]
2. [Analytical generalization — how findings extend theory]