Hierachial Modeling Approaches for Geographical Boundary Analysis in Cancer Studi

点击翻译按钮获取中文摘要

Boundary analysis concerns the detection and analysis of zones of abrupt change in spatial maps. Its importance in understanding scientific phenomena has been widely recognized in fields such as genetics and ecology. However, current methods are based upon rather ad-hoc deterministic algorithms. This project intends to develop formal statistical methods for carrying out boundary analysis, exploiting modern GIS tools to advance the development and interpretation of boundary analysis in spatial (cancer-related) maps. Attendant benefits of the project will include enhancements in the understanding of spatial structure associated with information displayed in cancer-related maps. Goals of this project include development of boundary analysis from an inferential perspective with evaluation of statistical modeling approaches using cancer data from the Minnesota Cancer Surveillance System (MCSS), the Iowa Women's Health Survey (IWHS), the Surveillance Epidemiology and End Results (SEER) (http://seer.cancer.gov) database of the National Cancer Institute, as well as Medicare usage and cancer hospice mortality data. Applications for environmental risk factor data from the Environmental Protection Agency (EPA) will also be carried out to draw toxin boundaries that may reveal interesting cancer-toxin relationships.