A Hierarchical Aggregate Data Model with Spatially Correlated Disease Rates

  1. Katherine A. Guthrie1,*,
  2. Lianne Sheppard2,*,
  3. Jon Wakefield3,*

Article first published online: 21 MAY 2004

DOI: 10.1111/j.0006-341X.2002.00898.x

Issue

Biometrics

Biometrics

Volume 58, Issue 4, pages 898–905, December 2002

Additional Information

How to Cite

Guthrie, K. A., Sheppard, L. and Wakefield, J. (2002), A Hierarchical Aggregate Data Model with Spatially Correlated Disease Rates. Biometrics, 58: 898–905. doi: 10.1111/j.0006-341X.2002.00898.x

Author Information

  1. 1

    Fred Hutchinson Cancer Research Center, 1100 Fairview Avenue N, Seattle, Washington 98109, U.S.A.

  2. 2

    Departments of Biostatistics and Environmental Health, Box 357232, University of Washington, Seattle, Washington 98195–7232, U.S.A.

  3. 3

    Departments of Biostatistics and Statistics, Box 357232, University of Washington, Seattle, Washington 98195–7232, U.S.A.

**email:kguthrie@fhcrc.org
**email:sheppard@u.washington.edu
***email:jonno@u.washington.edu

Publication History

  1. Issue published online: 21 MAY 2004
  2. Article first published online: 21 MAY 2004
  3. Received May 2002. Revised June 2002. Accepted June 2002.

SEARCH

SEARCH BY CITATION

ARTICLE TOOLS

Get PDF (920K)

Keywords:

  • Aggregate data analysis;
  • Bayesian disease mapping;
  • Ecological bias;
  • Spatial dependence

Summary. The aggregate data study design (Prentice and Sheppard, 1995, Biometrika82, 113–125) estimates individual-level exposure effects by regressing population-based disease rates on covariate data from survey samples in each population group. In this work, we further develop the aggregate data model to allow for residual spatial correlation among disease rates across populations. Geographical variation that is not explained by model predictors and has a spatial component often arises in studies of rare chronic diseases, such as breast cancer. We combine the aggregate and Bayesian disease-mapping models to provide an intuitive approach to the modeling of spatial effects while drawing correct inference regarding the exposure effect. Based on the results of simulation studies, we suggest guidelines for use of the proposed model.

Get PDF (920K)