Odds ratio
Say it: ODZ RAY-shee-oh
An odds ratio is a measure of association that compares the odds of an outcome or exposure in one group with the odds in another group.
Also: OR, odds ratios, relative odds, cross-product ratio
Definition
What is an odds ratio?
An odds ratio (OR) compares the odds of an event in one group with the odds of the same event in another. Odds are not the same as probability: they are the chance that something happens divided by the chance that it does not, so a probability of one in five gives odds of one to four. In a two-by-two table of exposure against disease, the odds ratio is the product of the two diagonal cells divided by the product of the other two, which is why it is also called the cross-product ratio.
An odds ratio of 1 means the exposure makes no difference to the odds of the outcome. A value above 1 means higher odds among the exposed, pointing to a possible risk factor, and a value below 1 means lower odds, pointing to a possible protective factor. A 95 percent confidence interval that excludes 1 is usually read as statistically significant. Like any measure of association, an odds ratio does not prove causation, because confounding factors can create a link.
The odds ratio is the standard measure for case–control studies, where true risks cannot be calculated. When a disease is rare, it closely approximates the risk ratio. Logistic regression also reports its results as odds ratios.
Practice it
Where you'll meet it
Related
Terms that go with it
- Case–control studyA case–control study is an observational study that compares people with a disease and people without it to find past exposures linked to it.
- Cohort studyA cohort study is an observational study that follows groups differing in an exposure over time to compare how often they develop an outcome.
- EpidemiologyEpidemiology is the study of how often diseases and other health events occur in populations, what causes them and how they can be controlled.
- IncidenceIncidence is the number of new cases of a disease that arise in a population at risk during a specified period of time.
- Genome-wide association studyA genome-wide association study (GWAS) scans the genomes of many people to find genetic variants that are more common in those with a trait or disease.
Sources
Checked against
Written for biofideX in plain words, after checking these references:
- CDC Principles of Epidemiology, Lesson 3 Section 5: Measures of Association
- Szumilas (2010), Explaining Odds Ratios
- NCI Dictionary of Cancer Terms: odds ratio
Last updated
Spotted a mistake? Tell us and we'll correct it.
Practice Epidemiology
Free epidemiology quizzes, with an explanation for every answer.
See the Quizzes