This paper presents an overview of analytic methods for estimating growth curves or developmental trajectories from longitudinal data. Traditional models for studying change are contrasted with a relatively new method, hierarchical linear models. Growth curve analyses of data from an early intervention project demonstrate the strengths and weaknesses of the various analytic methods. Using this example, evidence is presented indicating how hierarchical linear models can overcome some of the methodological limitations of other analytic techniques currently used to evaluate change.
