ABSTRACT
The creation of graphs allows for better visual feedback during the analysis of any given data set. This in turn permits better understanding of the data itself and highlights intuitively most of the outstanding features. In spatial epidemiology, this is called disease mapping. Complicated spatial information and hard-to-detect patterns can be easily visualised through disease maps in ways that could be missed in other representations. Bithell (2000), Diggle (2000), and Lawson (2001) reviewed different perspectives on disease mapping. Spatial epidemiology is focused on three different perspectives (Elliot et al., 2000; Lawson, 2001): (1) disease mapping; (2) disease clustering; and (3) geographical correlation analysis. These do not exhibit cleanly separated boundaries. For instance, a disease map can also be used to report the results of a geographical correlation study or to highlight areas of high or low disease incidence (i.e., locations of clusters in a cluster study) (Berke et al., 2002; Diggle, 2000).
