Odds ratio
- Measure
Compares the odds of having been exposed in cases and in controls; it is the measure of case-control studies.
What it is
The odds ratio (OR) is the ratio of two odds: the odds of exposure among cases and the odds of exposure among controls. It is the natural measure of the case-control study, where risks cannot be calculated, and it is also what logistic regression produces. When the outcome is rare (roughly under 10%), the OR is very close to the relative risk; when the outcome is common, the OR exaggerates it.
Formula and reading
- OR = (a/c) / (b/d) = (a×d) / (b×c).
- Odds of exposure in cases = a/c; in controls = b/d.
- The exposure OR equals the disease OR: (a/b)/(c/d) gives the same number.
- Read it like the RR: 1 neutral, above 1 linked to more outcome, below 1 to less.
Worked example
- Data: 100 cases of a rare liver disease and 200 controls. 40 cases and 30 controls used a pesticide.
- Table: a = 40, c = 60 (unexposed cases), b = 30, d = 170 (unexposed controls).
- Odds of exposure in cases = 40/60 ≈ 0.67; in controls = 30/170 ≈ 0.18.
- OR = (40 × 170) / (30 × 60) = 6,800 / 1,800 ≈ 3.8 (rounded to one decimal).
- Because the disease is rare, the OR approximates the relative risk.
- Reading: cases have about 3.8 times the odds of having used the pesticide compared with controls.
Relative risk versus odds ratio
| Feature | Relative risk (RR) | Odds ratio (OR) |
|---|---|---|
| Formula | [a/(a+b)] / [c/(c+d)] | (a×d) / (b×c) |
| Design | Cohort, clinical trial | Case-control, logistic regression (also cohorts) |
| What it compares | Risks | Odds |
| Common outcome | Direct value | Exaggerates the effect relative to the RR |
| Rare outcome | Direct value | Approximates the RR |
Markers
- OR
- odds
- 95% CI
How to read it
- Many studies of risk factors for rare diseases (uncommon cancers, birth defects) report ORs because they are case-control studies.
- When reading an OR of 3 for an outcome that affects 40% of patients, remember that the true RR is smaller.
Common pitfalls
- Calling an OR a risk when the outcome is common.
- Flipping the table and getting 1/OR.
- Confusing odds (0.25) with probability (20%).
Test yourself
Think of the answer, then tap the question to see it.
Cases: 30 exposed and 70 unexposed. Controls: 10 exposed and 90 unexposed. What is the OR?
OR = (30 × 90) / (70 × 10) = 2,700 / 700 ≈ 3.9.
When does the OR approximate the relative risk?
When the outcome is rare in the population studied (generally under 10%).
What odds does a 50% probability represent?
Odds of 1 (0.5 / 0.5): one to one.
Connections
Educational content on epidemiological and statistical methods; the examples use made-up numbers to teach the calculation. Not a clinical or legal guide: current Colombian rules are in the official sources.
Sources: Principles of Epidemiology | Lesson 3 - Section 5 (Centers for Disease Control and Prevention, 2012); Chapter 6: Choosing effect measures and computing estimates of effect (Cochrane, 2024).
Spotted a mistake?We are always improving for the community. Tell us what is wrong and our team will review it.Report a mistake
Representative model, for educational purposes only.