Stochastic differential equation based on a multimodal potential to model movement data in ecology. Issue 3 (24th October 2017)

• Record Type: Journal Article
• Authors: Gloaguen, Pierre; Etienne, Marie‐Pierre; Le Corff, Sylvain
• Is Part Of: Journal of the Royal Statistical Society. Volume 67:Issue 3(2018:May)
• Page Start: 599
• Page End: 619
• Publication Date: 2017-10-24
• Subjects: Exact simulation -- Global Positioning System data -- Local linearization -- Movement model -- Pseudolikelihood methods -- Stochastic differential equation; Statistics -- Periodicals; 519.5
• DOI: 10.1111/rssc.12251
• Languages: English
• ISSNs: 0035-9254

Abstract

Summary: The paper proposes a new model for individuals' movement in ecology. The movement process is defined as a solution to a stochastic differential equation whose drift is the gradient of a multimodal potential surface. This offers a new flexible approach among the popular potential‐based movement models in ecology. To perform parameter inference, the widely used Euler method is compared with two other pseudolikelihood procedures and with a Monte Carlo expectation–maximization approach based on exact simulation of diffusions. Performances of all methods are assessed with simulated data and with a data set of fishing vessel trajectories. We show that the usual Euler method performs worse than the other procedures for all sampling schemes.