Foundations & facets.

Facet theory is a metatheory for the multivariate behavioral sciences that posits that scientific theories and measurements can be advanced by discovering relationships between conceptual classifications of research variables and empirical partitions of data-representation spaces. For this purpose, facet theory proposes procedures for (1) Constructing or selecting variables for observation, using the mapping sentence technique (a formal definitional framework for a system of observations), and (2) Analyzing multivariate data, using data representation spaces, notably those depicting similarity measures (e.g., correlations), or partially ordered sets, derived from the data. Facet theory is characterized by its direct concern with the entire content-universe under study, containing many, possibly infinitely many, variables. Observed variables are regarded just as a sample of statistical units from the multitude of variables that make up the investigated attribute (the content-universe). Hence, Facet theory proposes techniques for sampling variables for observation from the entire content universe; and for making inferences from the sample of observed variables to the entire content universe.