A0751
Title: Cluster analysis for longitudinal data
Authors: Asael Fabian Martinez Martinez - Universidad Autonoma Metropolitana (Mexico) [presenting]
Ivonne Ramirez-Silva - Instituto Nacional de Salud Publica (Mexico)
Ruth Fuentes-Garcia - UNAM (Mexico)
Abstract: The identification of latent profile trajectories in longitudinal studies represents an important challenge for specialists. Many of the statistical methodologies are based on growth curve or mixed-effects models, and, for Bayesian nonparametric methods, Dirichlet process mixture models are widely used together. A clustering methodology is presented for longitudinal data based on mixture models generated by a discrete random probability measure whose weights are decreasingly ordered by construction. A straightforward procedure to merge some estimated groups is also provided, since it could happen that there are many of them to be easily explained by experts. The methodology is illustrated using simulated and real datasets.
