CMStatistics 2018: Start Registration
View Submission - CMStatistics
Title: Local depth measures for trajectories with a common origin Authors:  Lucas Fernandez Piana - Universidad de Buenos Aires and CONICET (Argentina)
Ana Justel - Universidad Autonoma de Madrid (Spain)
Marcela Svarc - Universidad de San Andres (Argentina) [presenting]
Abstract: The trajectories of common origin or back-trajectories appear very commonly in problems of meteorology and ecology, where the aim is to determine the origin of particles dragged by the winds that reach a certain point. We want to study arriving to the Byers Peninsula, located at the western coast of the Livingston Island (South Shetland Islands, Antarctica), to establish the dispersal capability of microorganisms susceptible of colonizing newly exposed locations in a climate change scenario. Local depths are extremely useful, because they allow us to adequately describe data which may not be unimodal. We will give an adequate definition of local depth for the problem in question based on considering local depth on circular data which is then properly integrated into a local depth measure for the back-trajectories. We will show its main properties and analyze its performance and computational aspects.