I n the last chapter, we introduced a three-level modeling framework for examining change in individuals and groups over time. Another variation on the basic three-level modeling framework is a multivariate multilevel model-that is, a model that has more than one dependent variable (defi ned at Level 1), with individuals at Level 2 and groups at Level 3. Th e multivariate multilevel model follows directly from the traditional single-level multivariate analysis of variance (MANOVA) model. One of the advantages of the multilevel formulation is that subjects with partial data on outcomes can be included in the analysis, which is a limitation of MANOVA (Hox, 2010). A second advantage is that the multivariate approach facilitates the development of more fl exible models with multiple response variables, which can have diff erent sets of explanatory variables (Wright, 1998). A third advantage is that the multivariate provides simultaneous estimation of the outcomes and adjustment for correlations between them. Moreover, it facilitates the use diff erent covariance structures at multiple levels along with a choice in methods to estimate them (Wright, 1998).