Variable - a finding that can take on different values during the course of a study. When used without specification, refers to a measurement taken as part of the study (e.g., AGE, AGREE, SEX). Variables should not to be confused with values, which represents realized measurements (e.g., 31, neutral, female).

There are numerous ways to classify variable, and no standard taxonomy exists. As used in this E-book, we speak of three classes of variables. These are:

Categorical variables with only two possible outcomes (e.g., SEX) are called binary, dichotomous, or indicator, variables.

Researchers also speak of the outcome variable (dependent variable, study outcome, "disease," Y) and main predictor variable (independent variable, explanatory variable, "exposure," X). For example, we may be interested in the effect of high blood pressure (predictor variable) on the incidence of cardiovascular disease mortality (outcome variable). All variable other than the study outcome and predictor are called extraneous variables or "potential confounders."