CFE 2019: Start Registration
View Submission - CMStatistics
Title: Spatio-temporal random partition models Authors:  Garritt Page - Brigham Young University (United States) [presenting]
Fernando Quintana - Pontificia Universidad Catolica de Chile (Chile)
David Dahl - Brigham Young University (United States)
Abstract: The number of scientific fields that regularly collect data that are temporally and spatially referenced continues to rapidly growth. An intuitive feature of spatio-temporal data is that measurements taken on experimental units near each other in time and space tend to be similar. As such, many methods developed to accommodate spatio-temporal dependent structures attempt to borrow strength among units close in space and time, which constitutes an implicit space-time grouping. Rather than implicitly performing this spatio-temporal grouping, we develop a class of dependent random partition models that explicitly models spatio-temporal clustering. Our model is a joint distribution for a sequence of random partitions indexed by time and space. We first detail how temporal dependence is incorporated so that partitions evolve gently over time. Then conditional and marginal properties of the joint model are derived. We then demonstrate how space can be integrated. Computation strategies are detailed and we illustrate the methodology through simulations and applications.