varycoef: An R Package for Gaussian Process-based Spatially Varying Coefficient Models

TL;DR

The paper introduces the R package varycoef, which facilitates estimation, prediction, and variable selection for Gaussian process-based spatially varying coefficient models, enabling flexible and interpretable analysis of spatial and time series data.

Contribution

The package implement state-of-the-art computational techniques for efficient modeling of spatially varying coefficients using Gaussian processes in R.

Findings

Efficient estimation of spatially varying coefficients on large datasets.

Versatile application to spatial and time series data.

Inclusion of variable selection and prediction features.

Abstract

Gaussian processes (GPs) are well-known tools for modeling dependent data with applications in spatial statistics, time series analysis, or econometrics. In this article, we present the R package varycoef that implements estimation, prediction, and variable selection of linear models with spatially varying coefficients (SVC) defined by GPs, so called GP-based SVC models. Such models offer a high degree of flexibility while being relatively easy to interpret. Using varycoef, we show versatile applications of (spatially) varying coefficient models on spatial and time series data. This includes model and coefficient estimation with predictions and variable selection. The package uses state-of-the-art computational statistics techniques like parallelization, model-based optimization, and covariance tapering. This allows the user to work with (S)VC models in a computationally efficient manner, i.e., model estimation on large data sets is possible in a feasible amount of time.