|
Abstract:
|
The ways animals interact with each other and the landscape they inhabit is of fundamental interest to wildlife ecologists. Snapshots of individual trajectories, observed using tracking devices such as radio collars, provide researchers with information about these important interactions and how they change over time. I describe a collection of novel, realistic statistical models that account for dependence in animal movement data both through time and among interacting individuals. The first model, demonstrated with an application to killer whales, allows researchers to make inference on a latent social network that describes dynamic social connections. The second model, applied to the movement of polar bears as they respond to seasonally changing sea ice, captures the behavior of individuals showing a preference for areas in a landscape near a complex-shaped, dynamic feature. The final model, applied to the movement of a mountain lion in Colorado, incorporates the dynamic behavior of an individual utilizing resources on a landscape in response to changing internal physiology.
|
