ABSTRACT
This chapter describes two methods for using growth curve analysis to analyze individual differences. The first method is simply an extension of multiple regression to the growth curve analysis framework: add the individual difference measure as a fixed effect into the growth curve model. The second method is to use the random effects to estimate individual participant effect sizes. Growth curve analysis provides a statistical tool to quantify systematic individual differences, which can then be used to extract new insights. The key difference is that in multilevel models, individual-level predictors are tested for their effect on the set of observations corresponding to that individual. The effect of phoneme awareness on baseline reading ability significantly improved model fit even when letter knowledge was already in the model, though again the improvement was substantially smaller. The chapter considers an extremely simple case to see how random effects provide a way to quantify individual effect sizes.
