Heteroscedastic conditional auto-regression models for areally referenced temporal processes for analysing California asthma hospitalization data

Harrison Quick, Bradley P. Carlin, Sudipto Banerjee

Research output: Contribution to journalArticlepeer-review

3 Scopus citations

Abstract

Often in regionally aggregated spatiotemporal models, a single variance parameter is used to capture variability in the spatial structure of the model, ignoring the effect that spatially varying factors may have on the variability in the underlying process. We extend existing methodologies to allow for region-specific variance components in our analysis of monthly asthma hospitalization rates in California counties, introducing a heteroscedastic conditional auto-regression model that can greatly improve the fit of our spatiotemporal process. After demonstrating the effectiveness of our new model via simulation, we reanalyse the asthma hospitalization data and note some important findings.

Original languageEnglish (US)
Pages (from-to)799-813
Number of pages15
JournalJournal of the Royal Statistical Society. Series C: Applied Statistics
Volume64
Issue number5
DOIs
StatePublished - Nov 2015

Keywords

  • Bayesian methods
  • Gaussian process
  • Gradients
  • Markov chain Monte Carlo methods
  • Spatial process models

Fingerprint Dive into the research topics of 'Heteroscedastic conditional auto-regression models for areally referenced temporal processes for analysing California asthma hospitalization data'. Together they form a unique fingerprint.

Cite this