spNNGP R package for Nearest Neighbor Gaussian Process models

TL;DR

The spNNGP R package offers scalable spatial regression models using Nearest Neighbor Gaussian Processes, enabling efficient analysis of large spatial datasets with Gaussian and non-Gaussian outcomes.

Contribution

This paper introduces the spNNGP R package, providing a comprehensive suite of NNGP models with MCMC and MCMC-free inference, including support for non-Gaussian data and parallel computing.

Findings

Effective modeling of large spatial datasets demonstrated.

Parallelization improves computational efficiency.

Applicability shown with simulated and real data.

Abstract

This paper describes and illustrates functionality of the spNNGP R package. The package provides a suite of spatial regression models for Gaussian and non-Gaussian point-referenced outcomes that are spatially indexed. The package implements several Markov chain Monte Carlo (MCMC) and MCMC-free Nearest Neighbor Gaussian Process (NNGP) models for inference about large spatial data. Non-Gaussian outcomes are modeled using a NNGP Polya-Gamma latent variable. OpenMP parallelization options are provided to take advantage of multiprocessor systems. Package features are illustrated using simulated and real data sets.