A Spectral Method for Identifiable Grade of Membership Analysis with Binary Responses

• Published in: Psychometrika Vol. 89; no. 2; pp. 626 - 657
• Main Authors: Chen, Ling, Gu, Yuqi
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.06.2024; Springer Nature B.V
• Subjects: Algorithms; Assessment; Bayes Theorem; Bayesian analysis; Behavioral Science and Psychology; Computer Simulation; Decomposition; Efficiency; Expectation; Humanities; Humans; Law; Mathematical models; Memberships; Models, Statistical; Personality Measures; Psychology; Psychometrics; Psychometrics - methods; Quantitative psychology; Simulation; Statistical Theory and Methods; Statistics for Social Sciences; Testing and Evaluation; Theory & Methods; Variables; spectral method; successive projection algorithm; grade of membership model; identifiability; latent variable model; singular value decomposition; mixed membership model

Grade of membership (GoM) models are popular individual-level mixture models for multivariate categorical data. GoM allows each subject to have mixed memberships in multiple extreme latent profiles. Therefore, GoM models have a richer modeling capacity than latent class models that restrict each sub...