|
Activity Number:
|
464
- SPEED: Infectious Diseases, Spatial Modeling and Environmental Exposures, Speed 1
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Wednesday, July 31, 2019 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
Section on Statistics in Epidemiology
|
|
Abstract #304641
|
Presentation
|
|
Title:
|
A Bayesian Hierarchical Model for Generating Fully Synthetic Point Process Data
|
|
Author(s):
|
Adam Walder*
|
|
Companies:
|
|
|
Keywords:
|
Point Process;
Spatial Statistics;
Synthetic Data;
Privacy;
Log Gaussian Cox Process;
Epidemiology
|
|
Abstract:
|
Confidential locations in epidemiological outbreak and crime occurrence data sets cannot be released to the public without privacy guarantees. Agencies intending to release such data must take measures to ensure the confidentiality of the subjects included in the data set. We implement a Bayesian hierarchical method for releasing fully synthetic data sets based on a log Gaussian cox process. We propose an intuitive and computationally efficient method for assessing risk, as well as a model-based approach to quantify the utility of the synthetic data set. We demonstrate our proposed methods with the use of the Jon Snow cholera outbreak mortality data set.
|
Authors who are presenting talks have a * after their name.
Back to the full JSM 2019 program
|
