PICAR: An Efficient Extendable Approach for Fitting Hierarchical Spatial Models

TL;DR

PICAR introduces a fast, scalable, and automated projection-based method for fitting hierarchical spatial models, significantly reducing computational costs and improving mixing in Bayesian inference, applicable across various scientific fields.

Contribution

The paper presents PICAR, a novel dimension-reduction approach using empirical basis functions that enhances efficiency and ease of implementation for hierarchical spatial models.

Findings

PICAR achieves faster mixing and lower computational costs in MCMC.

Simulation studies show accurate parameter inference and prediction.

Demonstrated applicability in diverse real-world spatial datasets.

Abstract

Hierarchical spatial models are very flexible and popular for a vast array of applications in areas such as ecology, social science, public health, and atmospheric science. It is common to carry out Bayesian inference for these models via Markov chain Monte Carlo (MCMC). Each iteration of the MCMC algorithm is computationally expensive due to costly matrix operations. In addition, the MCMC algorithm needs to be run for more iterations because the strong cross-correlations among the spatial latent variables result in slow mixing Markov chains. To address these computational challenges, we propose a projection-based intrinsic conditional autoregression (PICAR) approach, which is a discretized and dimension-reduced representation of the underlying spatial random field using empirical basis functions on a triangular mesh. Our approach exhibits fast mixing as well as a considerable reduction in computational cost per iteration. PICAR is computationally efficient and scales well to high dimensions. It is also automated and easy to implement for a wide array of user-specified hierarchical spatial models. We show, via simulation studies, that our approach performs well in terms of parameter inference and prediction. We provide several examples to illustrate the applicability of our method, including (i) a high-dimensional cloud cover dataset that showcases its computational efficiency, (ii) a spatially varying coefficient model that demonstrates the ease of implementation of PICAR in the probabilistic programming languages stan and nimble, and (iii) a watershed survey example that illustrates how PICAR applies to models that are not amenable to efficient inference via existing methods.