GIS 3015: Data Classification

This week I created four maps showing Miami Dade County, Florida.  These maps show different classification schemes involving the percentage of population within Miami Dade County. In the top left corner, it shows the natural breaks classification method.  In this method, class ranges are determined based on algorithms that attempts to make all values within a class as similar to each other as possible.  It also tries to make these values as different as possible to those values in other classes.  When using natural breaks, the graphs are examined visually to determine any breaks in the data.  Moving onto the next image in the top right, you'll see that this graph shows the equal interval classification method.  This approach creates classes that all have equal ranges in the data.  The range values are determined by dividing the total data range by the number of classes.  On the bottom left, you'll notice the quantile classification method is being used here.  This method divides the distribution into an equal number of observations. Using this approach, data is rank ordered and equal numbers of observation are placed in each class.  Although, using this method could cause gaps in your dataset and could make things difficult to comprehend for the viewer.  Finally, the standard deviation method puts the majority of observations in one class surrounding the average value, while other classes will have fewer and fewer data points as they get further away from the mean.  As you'll notice, this graphic is using a different color scheme then the ones surrounding it.  When using the standard deviation method, you'll want to use a divergent color scheme, so it clearly presents the diverging data.