Impact of violations of measurement invariance in cross-lagged panel mediation models

Abstract

When fitting cross-lagged panel mediation models, the assumption of longitudinal measurement invariance should be made. This simulation study investigated the impact of violations of measurement invariance on cross-lagged panel mediation analysis using the latent cross-lagged panel mediation model (L-CLPM). Results showed that estimates of direct and mediated effects tended to be less accurate and the type I error rate of testing mediated effects can be inflated under non-invariance conditions. On the other hand, power for detecting model misspecifications due to longitudinal non-invariance was high across all investigated conditions. Fit indices were not sensitive to violations of measurement invariance in the L-CLPM under the manipulated conditions. We end the article with suggestions, limitations, and future directions.