Data Classification Lab 4

The data classification lab focused on analyzing census data using four different classification methods. The four different classification methods included: Equal Interval, Quantile, Standard Deviation, and Natural Breaks. By using the same data with four different classification methods we were able to to see how differently data can be presented. 

Equal Interval: The equal interval classification class breaks are determined by dividing the range into desired number of equal-width class intervals. With the classes being divided into equal-width classes it makes the map easy to interpret and can help map complex spatial patterns. The classes do not consider the distribution of the data on a number line.

Quantile: The quantile classification equally divides the total number of values into the desired number of classes. An issue with using this method is that it can place similar values into different classes or different values in the same class.

Standard Deviation: The standard deviation classification forms classes by repeatedly adding or subtracting the standard deviation form the mean of the data. This method only works with data that is normally distributed and requires basic statistical knowledge.

Natural Breaks: The natural break classification considers natural groups within the data. It minimizes the difference between data values in the same class and maximizes the difference between classes. This method highlights extreme values placing outliers into their own classes which can cluster large number of values into one/two classes.

Figure 1 shows the senior population distribution in Miami Dade county Florida percent population about 65. 

Figure 1

Figure 2 shows the senior population distribution in Miami Dade county Florida total population above 65 normalized by square miles.

Figure 2

After comparing the maps I determined the equal interval classification method best displays the data for an audience. This map was the only one that broke along the data of the attribute table. This map is easy to interpret and the legend does not contain any gaps. I would use the population count normalized by square mile with the equal interval method to best present the distribution of seniors. With normalized data we can create more quality outputs taking into consideration and correcting spatial point-based measures and aggregate areal polygon features.