Editor Recommendation: Lianas and Soil Nutrients Predict Fine-Scale Distribution of Above-Ground Biomass in a Tropical Moist Forest

Post provided by Laura Graham



Datasets used by quantitative ecologists are getting more and more complex. So we need more complex models, such as hierarchical and complex spatial models. Typically, Bayesian approaches such as Markov chain Monte Carlo have been used. But these methods can be slow, making it infeasible to fit some models.

New developments in Integrated nested Laplace approximation (INLA) have made some of these complex models much faster to fit. Dedicated R packages (R-INLA and inlabru) make coding these Bayesian models much more straightforward. Also, INLA lets you fit of a class of models which allow for computationally efficient and flexible modelling of spatial data. Continue reading