When selecting a multilevel model to fit to a dataset, it is important to choose both a model that best matches characteristics of the data's structure, but also to include the appropriate fixed and random effects parameters. For example, when researchers analyze clustered data (e.g., students nested within schools), the multilevel model can be used to address the clustering in the data structure. In addition, if individuals are clustered in more than one cluster (e.g., students attend more than one school), the multiple-membership that results can be handled by use of the multiple-membership random effect model. Finally, if the data being analyzed includes multiple outcomes (e.g., math, science, and reading achievement scores), a multivariate model should be utilized to handle the dependence among multiple outcomes. If the data has both multiple-membership and multivariate outcomes, use of a multivariate multiple-membership random effects model (MV-MMREM, Beretvas, 2015; Park & Beretvas, 2017) could be used.