Case-Control Study: Definition and Example

A case-control study starts with people who have an outcome (cases) and people who do not (controls), then looks back to compare how often each group had an exposure. It is efficient for rare diseases and for outcomes that take a long time to develop.

How it works

1. Define the case definition clearly and identify cases.
2. Select controls from the same source population who could have become cases.
3. Measure past exposure using the same methods for both groups, ideally blind to case status.
4. Compare exposure between groups using the odds ratio (OR), with a confidence interval.
5. Adjust for confounders in the analysis, or match on them in the design.

Interpreting the odds ratio

An OR above 1 means the odds of exposure were higher among cases than controls. In case-control studies the odds ratio is the natural effect measure; when the outcome is rare, it approximates the relative risk. See Relative Risk vs Odds Ratio.

Illustrative example

Invented for teaching. In a hospital study, 120 patients with a rare liver condition (cases) are compared with 240 patients from the same hospital without it (controls). Past use of a herbal product is reported by 30 cases and 24 controls. The odds of exposure are 30/90 in cases and 24/216 in controls, so OR = (30/90)/(24/216) = 3.0, indicating a possible association that needs careful bias checking.

Strengths and limitations

Strengths: efficient for rare outcomes, fewer participants than cohort studies. Limitations: recall bias, selection bias in choosing controls, difficulty estimating incidence, and confounding. The choice of controls is the most common source of error.

Common pitfalls

• Controls drawn from a different population from cases.
• Using memory of exposure that differs because of case status.
• Reporting the odds ratio as if it were a risk ratio when the outcome is common.

Key takeaways

• Start from outcome, look back for exposure.
• Control selection and exposure measurement determine validity.
• The odds ratio is the standard measure.

This page is general educational information about research methods. It is not medical, legal or regulatory advice; follow your institution's ethics board and your target journal's instructions.