CHAID (Chi Squared Automatic Interaction Detection) is used to build a predictive model, based on a classification system. The analysis subdivides the sample into a series of subgroups that 1) share similar characteristics towards a specific response variable and that 2) maximises our ability to predict the values of the response variable.
The first predictor category (on which the sample will be split) is the predictor that is associated the most with the response variable. i.e. it gives the most differentiating groups of respondents. Each group is then further split until the analysis does not find any significantly discriminating predictor any more.
The predictors can be scaled (e.g. 1 to 10 scale rating) as well as categorical questions (e.g. company demographics).
The output is a tree of which the branches are the predictor variables that split the sample in discriminating groups.
CHAID is very often used to understand the characteristics of the most and least satisfied or interested customers or employees. It allows the client to target its (potential) clients more efficiently and successfully. CHAID analysis is typically used in the direct marketing industry to identify the type of people who have reacted to a specific campaign.