Modeling Heterogeneity of Latent Growth Depending on Initial Status.

The article focuses on the suggested modeling of heterogeneous latent growth curve to determine the differences in the growth rate of mathematical cognition of children in the U.S. The method of modeling and prediction is usually used for analysis of individual academic development by way of covariance structure. Researchers used math achievement data of grade 7 to 10 as subject for a longitudinal research on the heterogeneity of the children's academic growth rate with reference to their initial status. The suggested model is an extension of the conventional growth curve model and results of the research reflected that the proposed model is more accurate than the conventional growth model in giving confidence intervals in determining future math achievement of children.