Statistics Seminars: Animal movement modelling: overview of approaches and an example application to multiple bison movement paths
12 March 2012 14:00 in CM221
Analyzing animal movement is essential for understanding the animals' motivations, the dynamics of populations and their distribution in space. While the development of statistical methodology for animal movement data may have lagged behind the advancements in tracking technology, it is nevertheless also true that the last decade has seen substantial progress in terms of our ability to incorporate ecological realism in animal movement models.
My talk will be split into two parts. Part I gives an overview of some of the most popular approaches to modelling animal movement, including a discussion of their respective advantages and disadvantages. The talk will cover simple random walks, hidden Markov models (HMMs), Lévy walks and stochastic differential equations (with a focus on Ornstein-Uhlenbeck processes). In Part II of the talk I will discuss an example application of HMMs to movement paths of nine bison. I will also consider extensions of basic HMMs that (i) allow for more flexible distributions for the times the animals spend in the different motivational states and (ii) that involve random effects for capturing the heterogeneity across individuals.
Contact email@example.com for more information