W e propose a mixed effects statistical model to lea rn a distribution of shape trajectories from longi tudinal data\, i.e. the collection of individual o bjects repeatedly observed at multiple time-points . Shape trajectories and their variations are defi ned via the action of a group of deformations. The model is built on a generic statistical model for manifold-valued longitudinal data\, for which we propose to use a finite-dimensional set of diffeom orphisms with a manifold structure\, an efficient numerical scheme to compute parallel transport on this manifold and a specific sampling strategy for estimating shapes within a Markov Chain Monte Car lo (MCMC) method. The method allows the estimatio n of an average spatiotemporal trajectory of shape changes at the group level\, and the individual v ariations of this trajectory in terms of shape and pace of shape changes. This estimation is obtaine d by a Stochastic Approximation of the Expectation -Maximization (MCMC-SAEM). We show that the algori thm recovers the optimal model parameters with sim ulated 2D shapes. We apply the method to estimate a scenario of alteration of the shape of the hippo campus 3D brain structure during the course of Alz heimer'\;s disease. LOCATION:Seminar Room 1\, Newton Institute CONTACT:INI IT END:VEVENT END:VCALENDAR