GeoModels

Functions for Gaussian and Non Gaussian (bivariate) spatial and spatio-temporal data analysis are provided for a) (fast) simulation of random fields, b) inference for random fields using standard likelihood and a likelihood approximation method called weighted composite likelihood based on pairs and b) prediction using (local) best linear unbiased prediction. Weighted composite likelihood can be very efficient for estimating massive datasets. Both regression and spatial (temporal) dependence analysis can be jointly performed. Flexible covariance models for spatial and spatial-temporal data on Euclidean domains and spheres are provided. There are also many useful functions for plotting and performing diagnostic analysis. Different non Gaussian random fields can be considered in the analysis. Among them, random fields with marginal distributions such as Skew-Gaussian, Student-t, Tukey-h, Sin-Arcsin, Two-piece, Weibull, Gamma, Log-Gaussian, Binomial, Negative Binomial and Poisson. See the URL for the papers associated with this package, as for instance, Bevilacqua and Gaetan (2015) doi:10.1007/s11222-014-9460-6, Bevilacqua et al. (2016) doi:10.1007/s13253-016-0256-3, Vallejos et al. (2020) doi:10.1007/978-3-030-56681-4, Bevilacqua et. al (2020) doi:10.1002/env.2632, Bevilacqua et. al (2021) doi:10.1111/sjos.12447, Bevilacqua et al. (2022) doi:10.1016/j.jmva.2022.104949, Morales-Navarrete et al. (2023) doi:10.1080/01621459.2022.2140053, and a large class of examples and tutorials.

Last 30 days

Last 365 days

The following line graph shows the downloads per day. You can hover over the graph to see the exact number of downloads per day.