Abstract
Longitudinal and growth trajectory data analysis. Traditional approach and current proposals. In this article, the main models for analysing longitudinal and growth trajectory data are examined. We start from a traditional approach that include univariate and multivariate analysis of variance for repeated measures, to continue with generalized MANOVA and with two stage-multilevel model, which constitutes the basis for the development of the general linear mixed model. Lastly, multilevel models for longitudinal and growth trajectory data are studied. The main characteristics as well as assumptions of each model are described, trying to make it clear the reasons why the successive models have appeared and to establish the main similarities and differences between them. It is concluded that hierarchical linear models for longitudinal data constitute an excellent strategy to do applied research in the realm of social and behavioural sciences.
