Repeated measures longitudinal designs are important in determining outcomes in clinical and academic settings. However, such designs entail correlated (nested) and incomplete data sets. Hierarchical Linear Modeling allows researchers to formally represent multiple levels and specify how variables at one level influence occurrences at another. This presentation focuses on challenges to, and solutions for, longitudinal repeated measures designs. Handouts are provided and actual research examples will be detailed by way of data from a recent three-year longitudinal study.