“…INLA (Rue et al, 2009;Blangiardo and Cameletti, 2015) is a computationally efficient alternative to Markov chain Monte Carlo (MCMC) methods, which are usually adopted for Bayesian inference but suffer from computational complexity, especially in case of large datasets characterized by high spatial and/or temporal resolution. INLA performs approximate Bayesian inference for latent Gaussian models by using integrated nested Laplace approximations and its use is now well established in several research fields, including ecology, epidemiology, econometrics and environmental science (Illian et al, 2013;Blangiardo et al, 2013;Musenge et al, 2013;Bilancia and Demarinis, 2014;Carson and Mills Flemming, 2014;Cosandey-Godin et al, 2015;Bivand et al, 2014;Muff et al, 2015;Mtambo et al, 2015;Gómez-Rubio et al, 2015), also thanks to the availability of the R-INLA package.…”