Module 4: Data Classification

Module 4: Data Classification

In this weeks lab the focus was on the different data classification methods that can be used to represent data that are given to cartographers. The four classification methods that are common to use in ArcGIS Pro are Equal Interval, Quantile, Standard Deviation, and Natural Break. The Equal Interval classification method represents an equal amount of data values. The problem with the method is that there could be a class that contains no values and could be left blank. The Quantile classification method will never have empty classes or classes with few values. This method is good only if there are no outliers that can skew the data in one way or another. The Standard Deviation classification method is formed by adding/subtracting the standard deviation from the mean of your dataset. It is important to note that identical values cannot be in two different classes. A major disadvantage is that the data needs to be normally distributed to use the method. If the data is not normally distributed there could be classes that contain no values. The Natural Break classification method considers the natural groups within the dataset. Also, the method minimizes the differences between data values in the same class and maximizes the difference between classes. It is important to note that the method does consider outliers within the data and will place them in their own category. At the same time, it places clusters of data in one or more classes. Lastly, class breaks are up to the mapmaker with can make the map more subjective. Each one the classification methods have their advantages and disadvantages that the cartographer needs to make sure they are aware before representing the data.

There were two types of maps that are being represented in this weeks lab using the different classification methods. The first map is the percentage of people 65 and above in each of the census tracts. The classification method that best displays the data for an audience looking for is equal interval. The reason is because the classes are equal in their representation of the data. Also, it makes sure the outliers are not skewing the data in one way or another. Even though there are classes that do not have any data being represented it is still easy for the map reader to know what the census tracts represent. Lastly, the data is able to target the senior citizen population that has the highest amount of population in the census tracts.

The second map that is being represented is the population count normalized by area. This map is able to represent the actual numbers of the people 65 and above along with the area of the census tracts. When looking at the data being presented the map that accurately depicts the distribution of senior citizens is the Natural Breaks from the population count normalized by area. The reason for this is because it gives actual numbers and not a percentage of the population. Being able to see the actual numbers gives a better representation of the distribution of senior citizens. One potential issue of the other presentation method is that it is a percentage of the senior citizens compared to other age groups and not actual numbers. The numbers of senior citizens helps the map reader know how many actual people are in the census tract. Another potential issue is that the percentages are rounded to the second decimal point whereas the normalized group is either rounded to the first decimal point or a whole number. The last potential issue is that the numbers are based off the square miles of the census tracts and not just the percentage of the age group. Having the number relative to the area of the census tracts gives a better representation.

Data can be represented in many different ways and it is up to the cartographer to make sure it is being represented properly. The data can be represented by different classification methods such as Equal Interval, Natural Breaks, Quantile, or Standard Deviation. The cartographer has to make sure the data is not going to confuse the map reader or give them false interpretation of the data. Lastly, the cartographer needs to look at all the data before it is being represented to make sure they are not interpreting the information correctly.