Bayesian ACCESS for Understanding Latent Epidemic Trajectories from Publicly Released Suppressed Data: Application to U.S. Opioid-related Overdose Mortality
Abstract
Publicly released health statistics play a central role in characterizing temporal trends and identifying structural changes in population health. However, disclosure limitation through suppression of small cell counts, as implemented in systems such as the Centers for Disease Control and Prevention Wide-ranging ONline Data for Epidemiologic Research (CDC WONDER), produces partially observed count data that complicate statistical inference. These challenges are particularly acute for rare outcomes and subgroup analyses, where suppression is widespread and varies across geographic regions, demographic populations, and time. We propose Bayesian ACCESS (Autoregressive Change-point and Clustering Estimation for Suppressed Count Series), a Bayesian hierarchical framework for inference on latent epidemic trajectories and their structural changes from disclosure-limited health statistics. The proposed model directly represents suppressed count data through a suppression-aware observation model, jointly infers multiple temporal change points and latent trajectories, and borrows information across related geographic and demographic populations while preserving meaningful heterogeneity. We apply Bayesian ACCESS to opioid-related overdose mortality data from CDC WONDER for U.S. states from 1999 to 2024. The analysis identifies distinct subgroup-specific epidemic trajectories and structural changes that would be difficult to characterize using publicly released health statistics without explicitly accounting for data suppression and efficiently borrowing information across subgroups.
Related
- Empirical Bayes in Bayesian learning: understanding a common practice
- Understanding Hidden Spatial Preferences in Bayesian Optimization
- Uncertainty Quantification of State Variables Trajectories in the Context of Inverse Problems: An Approach from Bayesian Inference and FDA
- Hierarchical Bayesian Joint Modeling of Athlete Performance Trajectories and Latent Peak Ages
- Bayesian Recovery Trajectories Following Forced Sexual Experience: Healthcare Access and Social Support Among Women
BibTeX
@misc{cao2026bayesian,
title = {{Bayesian ACCESS for Understanding Latent Epidemic Trajectories from Publicly Released Suppressed Data: Application to U.S. Opioid-related Overdose Mortality}},
author = {Jiahao Cao and Kehe Zhang and Cici Bauer},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2608.09103},
eprint = {2608.09103},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2608.09103},
}
RIS
TY - UNPB
TI - Bayesian ACCESS for Understanding Latent Epidemic Trajectories from Publicly Released Suppressed Data: Application to U.S. Opioid-related Overdose Mortality
AU - Jiahao Cao
AU - Kehe Zhang
AU - Cici Bauer
PY - 2026
DA - 2026/10/23
PB - arXiv
DO - 10.48550/arxiv.2608.09103
UR - https://arxiv.org/abs/2608.09103
AB - Publicly released health statistics play a central role in characterizing temporal trends and identifying structural changes in population health. However, disclosure limitation through suppression of small cell counts, as implemented in systems such as the Centers for Disease Control and Prevention Wide-ranging ONline Data for Epidemiologic Research (CDC WONDER), produces partially observed count data that complicate statistical inference. These challenges are particularly acute for rare outcomes and subgroup analyses, where suppression is widespread and varies across geographic regions, demographic populations, and time. We propose Bayesian ACCESS (Autoregressive Change-point and Clustering Estimation for Suppressed Count Series), a Bayesian hierarchical framework for inference on latent epidemic trajectories and their structural changes from disclosure-limited health statistics. The proposed model directly represents suppressed count data through a suppression-aware observation model, jointly infers multiple temporal change points and latent trajectories, and borrows information across related geographic and demographic populations while preserving meaningful heterogeneity. We apply Bayesian ACCESS to opioid-related overdose mortality data from CDC WONDER for U.S. states from 1999 to 2024. The analysis identifies distinct subgroup-specific epidemic trajectories and structural changes that would be difficult to characterize using publicly released health statistics without explicitly accounting for data suppression and efficiently borrowing information across subgroups.
ER -