CAIMS Code of Conduct
“All participants are expected to comply with the CAIMS-SCMAI Code of Conduct”
Constructing Bayesian networks to discover probabilistic dependence between angler’s behaviour and auxiliary data
Understanding the relationships between variables, in terms of probabilistic dependence, plays a vital role in the conservation of ecosystems. However, the disclosure of such relationships in the field of ecology presents challenges due to the often large number of variables. The naive approach of testing every possible conditional independence among the variables can be computationally infeasible and results can be difficult to interpret. In this talk, we will explore the application of Bayesian networks (BNs) in the probabilistic dependencies among variables that can influence angler’s behaviour. BNs are directed acyclic graphs coupled with conditional probability distributions, where nodes represent random variables and directed edges represent probabilistic dependencies among the variables. They assert that each variable, given the state of its parents, is independent of its non-descendants in the graph. We examine data on angler’s behaviour obtained from citizen-reported activities and traditional field surveys, as well as auxiliary variables. We demonstrate how BNs can facilitate exploring relationships among the variables (e.g., catch rate, angler pressure, temperature, and median income).