Moving from exploratory to confirmatory network analysis: An evaluation of structural equation modeling fit indices...

Network models are well-suited for phenomena detection, and most empirical network studies have been exploratory so far. Yet, due to the close connections between (Gaussian) networks and structural equation modeling (SEM), confirmatory testing and SEM fit indices are readily applicable to network modeling as well. However, no study to date has evaluated how SEM fit indices perform in confirmatory network analysis (CNA), and what criteria should be applied. This study examined the applicability of SEM fit indices and their conventional cutoff values in CNA. We employed a panel graphical autoregressive model for its generalizability to network models in both cross-sectional (Gaussian graphical models) and N = 1 time-series cases (graphical autoregressive models). Using simulations, we analyzed the performance of fit indices to test hypothesized network structures and evaluate stationarity, under varying number of variables (nodes), sample sizes, and measurement waves. Most fit indices performed well, except that Type I incremental fit indices showed high false rejection rates. Conventional SEM cutoffs are largely generalizable to CNA as preliminary assessment criteria when dynamical cutoffs are unavailable. However, we recommend stricter cutoff values (e.g., 0.03/0.04 for the root-mean-square error of approximation [RMSEA] and 0.96/0.97 for incremental fit indices) in hypothesis testing or direct replication studies if researchers aim for more precise testing or exact replications. For detecting network structure non-stationarity, stricter RMSEA cutoffs (0.03/0.04) are advised. This study validates the use of SEM fit criteria for confirmatory network psychometrics and encourages theory-testing and replication studies in network research, providing practical recommendations for using SEM fit indices in confirmatory network testing. (PsycInfo Database Record (c) 2025 APA, all rights reserved).