Skip to content
My Glossary Project

Indicator Variable

TL;DR

Section titled “TL;DR”
  • Encodes the presence or absence of a characteristic using binary values.
  • Commonly used in statistical models to control for categorical attributes.
  • Easily incorporated into models such as regression analysis and analysis of variance.

Definition

Section titled “Definition”

An indicator variable, also known as a dummy variable, is a type of binary variable that takes on only two values: 0 and 1. This variable is often used in statistical modeling to represent the presence or absence of a certain characteristic or category.

Explanation

Section titled “Explanation”

Indicator variables represent whether a given characteristic or category applies to an observation by assigning a 1 when the characteristic is present and a 0 when it is absent. They allow researchers to evaluate the effect of that characteristic on an outcome while controlling for other factors (for example, diet and age). Indicator variables are straightforward to include in many statistical models, such as regression analysis and analysis of variance, which contributes to their widespread use.

Examples

Section titled “Examples”

Exercise example

Section titled “Exercise example”

Consider a study on the effects of exercise on weight loss. The researchers may use an indicator variable to represent whether or not a participant regularly exercises. This variable would take on the value of 0 if the participant does not regularly exercise, and 1 if they do. This allows the researchers to evaluate whether regular exercise has a significant effect on weight loss, controlling for other factors such as diet and age.

Education example

Section titled “Education example”

In a study on the effects of education on income, researchers may use an indicator variable to represent the highest level of education attained by each participant. This variable would take on the value of 0 if the participant did not graduate from high school, 1 if they graduated from high school but did not attend college, and 2 if they graduated from college. This allows the researchers to evaluate whether higher levels of education are associated with higher levels of income, controlling for other factors such as work experience and occupation.

Use cases

Section titled “Use cases”
  • Representing presence/absence of characteristics in statistical modeling.
  • Including categorical information as predictors in regression analysis.
  • Incorporating group membership or categories in analysis of variance.
Section titled “Related terms”
  • Dummy variable
  • Binary variable
  • Regression analysis
  • Analysis of variance
  • Statistical modeling