THE STATE OF THE ART ON STRUCTURAL EQUATION MODELING

Structural equation modeling (SEM) refers to a set of multivariate statistical techniques used to measure latent (unobserved) variables, which have been used more and more frequently.The study sought to analyze the current state of SEM disclosure, through technical articles.To this end, a review was carried out using the PRISMA method and data were collected in databases such as Scielo, APA PsycInfo, and Pepsic, with the descriptors SEM, Psychometrics, and review reports.Initially, 337 articles were found.However, only 16 were eligible for this research.It was found that the SEM promotes the expansion of multiple linear regression and confirmatory factorial analysis, combining these analyses.It was concluded that SEM is a robust and reliable statistical method that should be widely applied in health research, such as psychology, as it allows the technical analysis of research data.