Bayesian nonlinear structural equation modeling for hierarchical validation of dynamical systems

摘要: Abstract This paper presents a new Bayesian nonlinear structural equation modeling approach to hierarchical model assessment of dynamic systems, considering uncertainty in both predicted and measured time series data. A generalized with latent variables is presented two sets relationships multivariate assessment, namely, the computational system-level data, low-level data network Markov Chain Monte Carlo simulation Gibbs sampling developed represent estimate influencing factors between them. interval hypothesis testing-based method employed quantify confidence predictive at various levels. The effect on system level identified by inference factor analysis. proposed methodology implemented for validation three problems.