Modeling animal movement with directional persistence and attractive points

GPS technology is currently easily accessible to researchers, and many animal movement data sets are available. Two of the main features that a model which describes an animal’s path can possess directional persistence attraction point in space. In this work, we propose new approach have both characteristics. Our proposal hidden Markov with emission distribution. The distribution models two aforementioned characteristics, while latent state needed account for behavioral modes. We show easy implement Bayesian framework. estimate our on motivating represent locations Maremma Sheepdog recorded Australia. obtained results interpretable outperforms competitive model.