# Equal Interval Classification

This map has burgularies in 1998 as a proportion of the total population broken down into an equal interval classification with five classes.  The equal interval classification method simply divides the range of the data by the number of classes and to create an equal length interval between classes. A quantile classification would break up the classes to get an equal number of observations in each class.  The natural breaks or Jenks classification tries to class data in groups with the breaks at where the slope of the change in the data are highest.  The final continuous classification used by ArcMap is the optimal classification, which uses statistics to attempts to group data which are most similar.

# Standard Deviation

The mean and standard deviation classification is different from the classifications above because it is a divergent classification that classes the data into classes near the mean, (white) and various standard deviation differeances above (purple) and below (brown) the mean.  This scheme typically uses two color hues diverging to increasing saturation from the mean.

This graduated symbol map uses proportional symbols classed in this case into four different classifications based on the natural breaks or Jenks classification.  ArcView calls proportional symbols "graduated" when they are broken up into classes using one of the classification methods listed above.

# Proportional Symbols

This proportional symbol map shows the total number of burgularies in each district with a dot symbol that grows in size proportional to the number of events.  Since the actual number of events varies from a low of 4 to a high of 720, a map showing all values would appear overwhelmed in the tracts which had high numbers of burgularies.  Use of the exclude function for tracts which has less than 100 burgularies allows for a range of symbol sizes that leave the map readable.  A legend for this map would need to note that the non colored tracts had less than 100 burgularies.

# Proportional Pictographs

This map is essentially the same as above except that it uses pictographic symbols rather than generic dots or other shapes to represent the data.  While the symbol helps to identify the type of data, the varying shape of pictographs makes it more difficult to distinguish between different values.

# Dot Density Maps

Finally, this multivariate dot density map allows the reader to evaluate the density of crime events with regard to location and time by using a qualatative color ramp from light red for older events to dark red to more recent ones.