1. in regression analysis, a numerical variable that is created to represent a qualitative fact, which is done by giving a variable a value of 1 or 0 to indicate the presence or absence of a categorical trait. A dummy variable usually represents a dichotomous variable, that is, one that can have only two categories. For example, gender could be coded as a 1 to represent female and a 0 to represent male. When a measure has more than two categories, a researcher creates k − 1 dummy variables to represent the total number of different categories, k, with one of the categories indicated by 0.

2. in mathematics and computer science, a variable that can stand for or be bound to any element from its domain. Also called indicator variable.