Configural Frequency Analysis As a Statistical Tool for Defining Types

Configural frequency analysis (CFA) is a new method for identifying types. Types are defined as patterns (configurations) of binary variables occurring more frequently than may be expected under the assumption of complete independence of the respective variables, and are tested for significance by multiple binomial tests or suitable approximations. CFA is illustrated numerically by an example. Relations to latent class analysis and to factor analysis are discussed. It is suggested to use CFA as a type-defining method instead of factor analysis if the variables are linked to each other not only by first but also by higher-order associations.