Spatial analysis of relative risk of lip cancer in Iran: a Bayesian approach

✍ Scribed by A. Kavousi; M. Reza Meshkani; M. Mohammadzadeh

• Publisher: John Wiley and Sons
• Year: 2009
• Tongue: English
• Weight: 436 KB
• Volume: 20
• Category: Article
• ISSN: 1180-4009
• DOI: 10.1002/env.927

✦ Synopsis

Abstract

Providing a geographical map for rates of mortality, incidence, or prevalence of various diseases is of great importance for national health authorities. The relative risks are used to uncover the rate of incidence for different diseases. In the classical approach, the relative risk is often estimated under the assumption of independence between geographical areas. However, this assumption is not always substantiated in field studies, particularly in the case of health variables which may be strongly correlated due to common risk factors for adjacent areas. Such a dependence which is a function of distance between sample sites is called spatial correlation. In this paper, we account for such a dependence in evaluating the relative risk. This is undertaken by employing a hierarchical Bayesian approach. The proposed method is illustrated by a real example of lip cancer in Iran. The estimated relative risks and their standard errors (SEs) are computed. The distributional map of the disease and its SE are provided. Copyright © 2008 John Wiley & Sons, Ltd.