Association

How it is used

Researchers find, observe or report an association, then judge whether it is causal using criteria such as strength, consistency, timing and dose-response, often called the Bradford Hill criteria. 'Association is not causation' is a common warning.

Example sentences

1. We found a strong association between poor housing and childhood asthma.

2. The association disappeared after we adjusted for income.

Common collocations

• strong association
• causal association
• association between
• dose-response relationship

Related terms

• confoundingA distortion that happens when a third factor is linked to both the exposure and the outcome, making their relationship look stronger, weaker or different than it really is.
• risk factorA characteristic, behaviour or exposure that increases the chance of developing a disease or health problem, such as smoking, high blood pressure or poor housing.
• odds ratioA measure of association that compares the odds of an exposure among cases with the odds among controls, or the odds of an outcome in two groups.
• observational studyA study in which researchers observe and measure people's exposures and outcomes without assigning any treatment or intervention themselves.

More terms: Bias, Causation and Data Analysis

• exposure
• bias
• relative risk
• confidence interval
• selection bias