Spatial Thinking in Planning Practice: An Introduction to GIS

34 map or interpreting one created by someone else. Many di#erent systematic classi!cation schemes have been developed. Some produce mathematically “optimal” classes for unique data sets, maximizing the di!erence between classes and minimizing di!erences within classes . Since optimizing schemes produce unique solutions, however, they are not the best choice when several maps need to be compared. For this, data classi!cation schemes that treat every data set alike are preferred. Figure 4.11. Portion of the ArcMap classi!cation dialog box highlighting the schemes supported in ArcMap 8.2. Source: Department of Geography, "e Pennsylvania State University. Two commonly used classi!cation schemes are quantiles and equal intervals. "e following two graphs illustrate the di#erences. Figure 4.12. County population change rates divided into !ve quantile categories. Source: Department of Geog- raphy, "e Pennsylvania State University. "e graph above groups the Pennsylvania county population change data into !ve classes, each of which contains the same number of counties (in this case, approximately 20 percent of the total in each). "e quantiles scheme accomplishes this by varying the width, or range, of each class. Quantile is a general label for any grouping of rank ordered data into an equal number of entities; quantiles with speci!c numbers of groups go by their own unique labels (“quartiles” and “quintiles,” for example, are instances of quantile classi!cations that group data into four and !ve classes respectively). "e !gure below, then, is an example of quintiles. Chapter 4: Mapping People with Census Data