The ability to evaluate geographic heterogeneity of cancer incidence and mortality is important in cancer surveillance. Exploring the relationships between cancer rates and associated regional environmental factors, health care, and social economic status has proven to be beneficial in understanding cancer risk and providing preventable measures. Many statistical methods are available for spatial heterogeneity. In this talk, we focus on two aspects: global clustering evaluation and local anomaly (outlier) detection. We compare methods for global clustering evaluation including Tango’s Index, Moran’s I, and Oden’s Ipop; and cluster detection methods such as local Moran’s I and SaTScan elliptic version on simulated count data that mimic global clustering patterns and outliers for cancer cases in the continental United States. We examine the power and precision of the selected methods in the purely spatial analysis. We also illustrate Tango’s MEET and SaTScan elliptic version on a 1987-2004 HIV and a 1950-1969 lung cancer mortality data in the United States. Finally, we present a modified version of Moran’s I that we developed which has a higher power than the original Moran’s I and Ipop.
Back to IPC Short Course: Operations Research or the Mathematics of Strategic Decision Making