Spatial Scan Statistics for Models with Excess Zeros and Overdispersion

Authors

  • Max Sousa de Lima Universidade Federal do Amazonas
  • Luiz H. Duczmal Universidade Federal de Minas Gerais
  • Leticia P. Pinto Universidade Federal de Minas Gerais

DOI:

https://doi.org/10.5210/ojphi.v5i1.4528

Abstract

Spatial Scan Statistics usually assume Poisson or Binomial distributed data, which is not realistic in many disease surveillance scenarios. We propose a statistical model for disease cluster detection, through a modification of the spatial scan statistic to account for inflated zeros and overdispersion simultaneously. A computer program is implemented using the Expectation-Maximization algorithm to solve the latent variables. Numerical simulations are shown to assess the effectiveness of the method. We present results for Hanseniasis surveillance in the Brazilian Amazon using this technique, compared with other models.

Author Biography

Luiz H. Duczmal, Universidade Federal de Minas Gerais

Luiz Duczmal is Associate Professor in the Statistics Department at Universidade Federal de Minas Gerais, Brazil. His main research interests are spatial statistics, spatial cluster detection, optimization and operational research.

Downloads

Published

2013-03-23

How to Cite

Sousa de Lima, M., Duczmal, L. H., & Pinto, L. P. (2013). Spatial Scan Statistics for Models with Excess Zeros and Overdispersion. Online Journal of Public Health Informatics, 5(1). https://doi.org/10.5210/ojphi.v5i1.4528

Issue

Section

Oral Presentations: Temporal or Spatio-temporal