Online Program Home
My Program

Abstract Details

Activity Number: 358 - Contributed Poster Presentations: Section on Statistics in Epidemiology
Type: Contributed
Date/Time: Tuesday, July 30, 2019 : 10:30 AM to 12:20 PM
Sponsor: Section on Statistics in Epidemiology
Abstract #307064
Title: Bayesian Hierarchical Modeling for Under-Reported Spatial Count Data
Author(s): Jinjie Chen* and James D Stamey and Joon Jin Song
Companies: Baylor University and Baylor University and Baylor University
Keywords: Under-reported ; Spatial ; Bayesian ; Binomial-thinned; BYM
Abstract:

Spatial count data are commonly observed in many fields in the social sciences and public health. However, these data are often under-reported due to flawed data collection processes, which is usually inevitable. Under-reported data can lead to biased statistical inferences, which influences important decision making. The objective of this study is to propose a Bayesian Hierarchical approach for correcting underreporting in spatial count data. We model the counting process through binomial-thinned Poisson distribution. Areal spatial random effects are incorporated into the Poisson modeling using BYM2 model given ICAR prior. Bayesian analysis is adopted in the simulation to examine the impact of under-reporting and spatial dependence on statistical inference. We also apply the proposed model to real-world datasets.


Authors who are presenting talks have a * after their name.

Back to the full JSM 2019 program