Epidemiology · Reference
What is a case-control study?
A case-control study is an observational design that starts from the outcome: it compares people who have a condition (cases) with people who do not (controls), looking back at their past exposures. It is efficient for rare outcomes and yields an odds ratio.
How a case-control study works
A case-control study works backwards relative to a cohort study. The investigator first selects cases — people who already have the outcome — and controls — comparable people who do not — then looks back to compare how often each group was exposed to the factor of interest. Because participants are chosen by outcome status, the study cannot observe new cases arising and so cannot compute incidence or risk directly. Instead, the association between exposure and outcome is summarised by an odds ratio, which approximates the relative risk when the outcome is rare.
Choosing cases and controls
The validity of a case-control study hinges on how cases and controls are selected. Controls should come from the same source population as the cases and represent the exposure distribution of the population that produced the cases. Getting this wrong introduces selection bias.
Exposure is usually ascertained after the outcome has occurred, often from records or recall, which makes the design vulnerable to recall bias — cases may remember or report past exposures differently from controls. Careful, comparable measurement of exposure in both groups is therefore essential.
Strengths and limitations
Case-control studies are efficient for rare outcomes: by sampling on outcome, they assemble enough cases without following a huge population for years, so they are usually quicker and cheaper than cohort studies. They can also examine several exposures for a single outcome. Their limitations follow from the design: they are prone to selection and recall bias, they cannot measure incidence or absolute risk, and the temporal sequence between exposure and outcome can be harder to establish. They are also less suited to studying rare exposures, which cohort designs handle better.
When the design is used
The case-control design is a workhorse of epidemiology, especially for investigating rare diseases, outbreaks, and conditions with long latency, where waiting for outcomes to accrue in a cohort would be impractical. Historically it has been pivotal in identifying causes of uncommon conditions. As with all observational research, findings indicate association rather than proven causation and require attention to confounding. Reporting in line with the STROBE guidelines helps readers assess how cases and controls were chosen and how exposure was measured.
Key facts
At a glance
- Type: Observational analytic study
- Direction: Outcome → exposure (looks backward)
- Measure: Odds ratio (not incidence or risk)
- Best for: Rare outcomes and long-latency conditions
- Key biases: Selection bias and recall bias
Common questions
FAQ
How is a case-control study different from a cohort study?+
A case-control study starts from the outcome, comparing people who have a condition with those who do not and looking back at past exposures, whereas a cohort study starts from exposure and follows people forward to see who develops the outcome. Case-control studies yield odds ratios; cohort studies can measure incidence and relative risk.
Why does a case-control study use an odds ratio?+
Because participants are selected by their outcome status rather than followed from exposure, a case-control study cannot observe incidence and so cannot calculate risk or relative risk directly. The odds ratio can be estimated from the design and, when the outcome is rare, approximates the relative risk.
What biases affect case-control studies most?+
Selection bias arises if controls are not drawn from the same population that produced the cases, and recall bias arises if cases and controls report past exposures differently. Careful selection of controls and comparable exposure measurement are central to a valid case-control study.
The step most authors miss
Doing CRediT right? Don’t stop at the statement.
A CRediT statement credits you inside one paper. The recognition CRediT was built for happens when those roles are tied to you, persistently. Sign in with your ORCID — free — and claim your CRediT contributions on casrai.org, the home of the standard. They become a verified, portable part of your identity, not a line that disappears into one PDF.
Free: claim your contributions, then export a journal-ready CRediT statement, schema.org structured data, JATS XML, CSV or BibTeX — and preview your public profile. A membership publishes that profile publicly and verifies the journals you serve.
