Home/Insights/Methodology reference/Case study research methodology
Case study research methodology
An in-depth investigation of one case in its real context. Its generalisation is to theory, not to a population, and conflating the two is the usual criticism.
What defines it
A case study examines a contemporary phenomenon in depth within its real-world setting, particularly where the boundary between phenomenon and context is unclear. The case may be a person, a team, an organisation, a programme or an event.
It is a research design, not a data collection method. Case studies typically draw on several sources — interviews, documents, observation, records — and converge them.
Single and multiple cases
A single case is justified when it is critical (it tests a well-formulated theory), extreme or unique, revelatory (previously inaccessible), or longitudinal.
Multiple cases permit replication logic: cases are selected to predict either similar results (literal replication) or contrasting results for anticipated reasons (theoretical replication). Cases are not a sample and should not be described as one.
Analytic generalisation
This is the point most often misunderstood. A case study generalises to theoretical propositions, not to populations. The finding is that a mechanism operates in a particular way under particular conditions, which extends or challenges a theory.
Writing "these findings may not generalise to other settings" as a limitation misstates the design: statistical generalisation was never the claim.
Rigour
Construct validity through multiple sources and a maintained chain of evidence. Internal validity through pattern matching and explanation building where causal claims are made. External validity through replication logic. Reliability through a case study protocol and a case study database, so another researcher could follow the same path.
The protocol and database are what separate case study research from an extended anecdote.
In practice
Fix, flag or query.
The distinction that keeps an edit defensible: what an editor may change silently, what must be shown to the author, and what only the author can answer.
- Do not describe: cases as a sample.
- Maintain: a case study protocol and database.
- Claim: analytic generalisation to theory, not statistical generalisation.
Reporting standards
- Yin, Case Study Research and Applications, on design and replication logic
- SRQR, Standards for Reporting Qualitative Research
Reporting guidelines named here are hosted by the EQUATOR Network. Writing to the checklist for your design before submission is the cheapest available improvement to a methods section.
Related