Confirmatory Factor Analysis
Joop J. Hox · The Encyclopedia of Research Methods in Criminology and Criminal Justice · 2021
Factor analysis is a technique that assumes that the correlations between a set of observed variables can be modeled by a much smaller set of unobserved or latent variables called factors. Factor analysis comes in two forms: explorative and confirmatory. Confirmatory factor analysis (CFA) assumes that the researcher has a strong theory about the structure of the concept under investigation. CFA is part of a more general technique called structural equation modeling. CFA serves two purposes: first, to assess how well a specific model fits the data; second, to estimate the factor loadings, variances, and covariances of the factor(s), and the residual error variances of the observed variables. All goodness-of-fit measures are a function of the chi-square and the degrees of freedom.