Bayesian spatiotemporal conditional autoregressive model for local temporal variations
Abstract
Spatiotemporal areal data are commonly observed in various fields such including epidemiology, social science, economics and so on. To capture both spatial trends and temporal trends, spatiotemporal modeling is often employed, and the conditional autoregressive (CAR) model is one of the most widely used approaches for modeling areal data. This paper proposes a new framework for estimating spatiotemporal trends based on the CAR model. The proposed method provides locally adaptive temporal smoothing while yielding interpretable temporal trends by effectively utilizing information from both spatially neighboring areas and temporally adjacent time points. We also develop a Gibbs sampling algorithm and demonstrate the ability of the proposed method to adapt to to local temporal changes through numerical examples.
Related
- Realized Tail-Risk Conditional Autoregressive Expectile Models: Accurate and Stable Forecasting Performance
- Joint Conditional Maximum Likelihood Estimation of Beta Regression for Panel Data with Higher-Order Autoregressive Errors
- Bayesian Generalized Network Autoregressive Model with Structured Shrinkage and Persistence Priors
- glmSTARMA -- An R-Package for fitting autoregressive spatio-temporal models following generalized linear models
- Scalable generative modeling of non-Gaussian spatio-temporal fields via autoregressive Gaussian processes
BibTeX
@misc{onizuka2026bayesian,
title = {{Bayesian spatiotemporal conditional autoregressive model for local temporal variations}},
author = {Takahiro Onizuka and Shintaro Hashimoto},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.05817},
eprint = {2609.05817},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.05817},
}
RIS
TY - UNPB
TI - Bayesian spatiotemporal conditional autoregressive model for local temporal variations
AU - Takahiro Onizuka
AU - Shintaro Hashimoto
PY - 2026
DA - 2026/09/05
PB - arXiv
DO - 10.48550/arxiv.2609.05817
UR - https://arxiv.org/abs/2609.05817
AB - Spatiotemporal areal data are commonly observed in various fields such including epidemiology, social science, economics and so on. To capture both spatial trends and temporal trends, spatiotemporal modeling is often employed, and the conditional autoregressive (CAR) model is one of the most widely used approaches for modeling areal data. This paper proposes a new framework for estimating spatiotemporal trends based on the CAR model. The proposed method provides locally adaptive temporal smoothing while yielding interpretable temporal trends by effectively utilizing information from both spatially neighboring areas and temporally adjacent time points. We also develop a Gibbs sampling algorithm and demonstrate the ability of the proposed method to adapt to to local temporal changes through numerical examples.
ER -