We’ve added a new video to our YouTube channel today, entitled “Understanding the causes and consequences of animal movement” by John Fieberg and Mark Ditmer.

In this video, John discusses some of the challenges associated with inferring causal relationships among animal movement characteristics and indicators of an animal’s physiological condition.  Specifically, John and Mark explore models that relate estimates of daily movement rates to average daily heart rates (collected using surgically implanted heart monitors) in conjunction with a biotelemetry study involving black bears (Ursus americanus).  They show that estimates of regression parameters are sensitive to the assumed error structure, they suggest this sensitivity is due to endgoeneity of the predictor variable(s), and they use directed acyclical graphs to develop potential explanations for the observed endogeneity. The implications of this work are relevant to most studies that make use of biotelemetry data.

You can read the accompanying forum article published in Methods here: Understanding the causes and consequences of animal movement: a cautionary note on fitting and interpreting regression models with time-dependent covariates.