Questionable Mediated Effect of Peer Victimization on Prosocial Behavior in Adolescents: A Reanalysis of Guo et al. (2026)

Using the covariance matrix reported by Guo et al., we reassessed the evidence supporting their mediation model linking peer victimization to lower levels of prosocial behavior among adolescents. We demonstrate that the empirical associations can be reproduced with high accuracy by an alternative latent-variable model that does not depend on the order of influence proposed in the original article. In this model, self-reported peer victimization, psychological capital, empathy, and prosocial behavior are conceptualized as indicators of a broader latent construct, namely core self-evaluation. The findings illustrate a fundamental issue in observational research: different theoretical models may account equally well for the same covariance structure. Consequently, correlational data alone provide limited grounds for favoring one specific explanatory mechanism over competing alternatives. Consequently, researchers should consider alternative specifications before drawing strong conclusions about underlying processes.