Our model is based on Structural Equation Modeling (SEM), which is a powerful combination of statistical techniques, including path analysis, confirmatory factor analysis (CFA), and multivariate regression. Path diagrams are a critical feature of SEM, visually representing the hypothesized relationships between variables. The structure of the model includes a 'measurement' model, which predicts latent variables, and a 'structural' model, which defines the relationships between latent variables and observed variables that are not indicators. In this specific model, the latent construct 'reliance' is used to analyze resilience to great power influence.

Our model utilizes Maximum Likelihood Estimation (MLE) as the criterion for parameter estimation. MLE minimizes the differences between the sample covariance matrix and the covariance matrix derived from the hypothesized model. This process ensures the model's convergence by requiring the covariance matrix to be positive definite, thereby avoiding linear dependence between indicators and latent constructs.

Factor loadings indicate the strength of the relationship between observed variables and latent factors. Higher factor loadings suggest a stronger relationship. The square of the factor loadings represents the proportion of variance in the observed variable explained by the latent factor.

While both SEM and Principal Component Analysis (PCA) involve latent variables and data dimensionality reduction, there are critical differences between them. PCA derives principal components to maximize variance explained, but SEM models latent variables as theoretical constructs of interest. These latent variables are linked to observed indicators based on hypothesized causal models, which allows SEM to test specific causal relationships that PCA cannot address.