I recently jumped into Bayesian analysis and Integrated Species Distribution Modelling. Here’s the preprint out of an amazing collaboration with Diana Bowler and Petr Keil: ‘Integrating presence-only and presence-absence data to model changes in species geographic ranges: An example of yaguarundí in Latin America’. 🐈 🌎 ⏳
The are no standard methods to assess the performance of these models, yet posterior predictive checks are a good option. For our model we needed a statistic that fitted a binomial regression, to assess the performance on the presence-absence data.