The Impact of Ignoring a Level of Nesting Structure in Multilevel Mixture Model

Mixture modeling has gained more attention among practitioners andstatisticians in recent years. However, when researchers analyze their data using finitemixture model (FMM), some may assume that the units are independent of each other eventhough it may not always be the case. This article used simulation studies to examinethe impact of ignoring a higher nesting structure in multilevel mixture models. Resultsindicate that the misspecification results in lower classification accuracy ofindividuals, less accurate fixed effect estimates, inflation of lower level varianceestimates, and less accurate standard error estimates in each subpopulation, the latterresult of which in turn affects the accuracy of tests of significance for the fixedeffects. The magnitude of the intraclass correlation (ICC) coefficient has a substantialimpact. The implication for applied researchers is that it is important to model themultilevel data structure in mixture modeling