Latent Variables in Psychology and the Social Sciences

TLDR

The paper reviews latent variable concepts in psychology and social sciences, outlining definitions such as local independence, true‑score expectation, and nondeterministic functions, and examines how these definitions vary across diverse application areas. The authors describe identification, indeterminacy, and common properties of latent variable models and review their application across multiple regression, probit/logistic regression, factor analysis, latent curve models, item response theory, latent class analysis, and structural equation modeling. The study evaluates existing latent variable definitions, introduces an alternative sample‑realization definition, and assesses their properties.

Abstract

▪ Abstract The paper discusses the use of latent variables in psychology and social science research. Local independence, expected value true scores, and nondeterministic functions of observed variables are three types of definitions for latent variables. These definitions are reviewed and an alternative “sample realizations” definition is presented. Another section briefly describes identification, latent variable indeterminancy, and other properties common to models with latent variables. The paper then reviews the role of latent variables in multiple regression, probit and logistic regression, factor analysis, latent curve models, item response theory, latent class analysis, and structural equation models. Though these application areas are diverse, the paper highlights the similarities as well as the differences in the manner in which the latent variables are defined and used. It concludes with an evaluation of the different definitions of latent variables and their properties.