A Multi-Rater Latent Growth Curve Model

To avoid the subjectivity of having a single person evaluate a construct of interest (e.g., a student's self-efficacy in school), multiple raters are often used. Increasingly, data that use multiple raters to evaluate psychological and social-emotional constructs over time are available. While a range of models to address measurement issues that arise when using multiple raters have been presented, including a small number for longitudinal data, few if any models are available to estimate growth in the presence of multiple raters. In this study, we provide a model that removes all but the shared perceptions of raters at a given timepoint (i.e., removes unique rater variance), then adds on a latent growth curve model across timepoints. Through simulation and empirical studies, we examine the performance of the model in terms of recovering true growth parameters, and relative to more crude approaches like estimating growth based on a single rater. Our results indicate that the model we propose performs quite well along these dimensions, and shows promise for use by researchers who want to estimate growth based on longitudinal multi-rater data.