Online Program Home
  My Program

All Times EDT

Abstract Details

Activity Number: 458 - Models for Spatial and Environmental Data
Type: Contributed
Date/Time: Thursday, August 6, 2020 : 10:00 AM to 2:00 PM
Sponsor: Section on Statistics and the Environment
Abstract #310936
Title: Recovering Individual-Level Spatial Inference from Aggregated Binary Data
Author(s): Nelson Walker* and Trevor J Hefley and Anne Ballmann and Robin Russell and Daniel Walsh
Companies: Kansas State University and Kansas State University and U.S. Geological Survey - National Wildlife Health Center and U.S. Geological Survey - National Wildlife Health Center and U.S. Geological Survey - National Wildlife Health Center
Keywords: Change of support; Differential privacy; Ecological fallacy; Group testing; Logistic regression; Poisson point process
Abstract:

Binary regression models are commonly used in disciplines such as epidemiology and ecology to make individual-level inference on spatial covariates. In many studies, binary data are shared in a spatially aggregated form to protect privacy. Often, the spatial aggregation process obscures the values of response variables, spatial covariates, and locations of each individual, which makes recovering individual-level inference difficult. We show that applying a series of transformations to a bivariate point process model allows researchers to recover individual-level inference for spatial covariates from spatially aggregated binary data. The series of transformations preserves the convenient interpretation of desired binary regression models that are commonly applied to individual-level data. Using a simulation experiment, we compare the performance of our proposed method applied to spatially aggregated binary data against the performance of standard approaches using the original individual-level data. We illustrate our method by modeling individual-level disease risk in a population using a data set that has been aggregated for privacy protection.


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

Back to the full JSM 2020 program