Predictive Discriminant Analysis

Predictive discriminant analysis (DA, also called linear discriminant analysis) predicts group membership of observations that are described by several quantitative variables and when the group membership of (at least some) the observations is known a priori. The variables describing the observations are also called predictors or independent variables. DA is closely related to analysis of variance (ANOVA) and multivariate analysis of variance (MANOVA whose defining equations are formally equivalent to DA). Specifically, ANOVA and MANOVA use a qualitative independent variable (i.e., group membership) to predict one or more quantitative variables, whereas DA uses one or more quantitative variables (i.e., the predictors) to predict a qualitative dependent variable (group membership).

The Main Idea

With J a priori groups, DA linearly combines the predictors to create a set ...

  • Loading...
locked icon

Sign in to access this content

Get a 30 day FREE TRIAL

  • Watch videos from a variety of sources bringing classroom topics to life
  • Read modern, diverse business cases
  • Explore hundreds of books and reference titles