Scalable Bayesian modeling for smoothing disease risks in large spatial data sets

Abstract

Several methods have been proposed in the spatial statistics literature for the analysis of big data sets in continuous domains. However, new methods for analyzing high-dimensional areal data are still scarce. Here, we propose a scalable Bayesian modeling approach for smoothing mortality (or incidence) risks in high-dimensional data, that is, when the number of small areas is very large. The method is implemented in the R add-on package bigDM. Model fitting and inference is based on the idea of "divide and conquer" and use integrated nested Laplace approximations and numerical integration. We analyze the proposal's empirical performance in a comprehensive simulation study that consider two model-free settings. Finally, the methodology is applied to analyze male colorectal cancer mortality in Spanish municipalities showing its benefits with regard to the standard approach in terms of goodness of fit and computational time.

References in corpus (6)

• A general framework for Vecchia approximations of Gaussian processes
• A multi-resolution approximation for massive spatial datasets
• Discussion on Computationally Efficient Multivariate Spatio-Temporal Models for High-Dimensional Count-Valued Data by Bradley et al
• Parallelizing Gaussian Process Calculations in R
• Parallel inference for massive distributed spatial data using low-rank models
• New frontiers in Bayesian modeling using the INLA package in R

Cited by in corpus (5)

• Big problems in spatio-temporal disease mapping: methods and software
• High-dimensional order-free multivariate spatial disease mapping
• A scalable approach for short-term disease forecasting in high spatial resolution areal data
• A fast approach for analyzing spatio-temporal patterns in ischemic heart disease mortality across US counties (1999-2021)
• The complexity of finding and enumerating optimal subgraphs to represent spatial correlation