Module 4: Data Classification
Module 4: Data Classification
For this week's module, we practiced using four data classification methods for two types of data. We used the equal-interval, quantile, standard deviation, and natural-break classification methods on the percentage of residents over 65 (first image) and the number of residents over 65 per square mile (second image). Equal interval distributes data into a set number of intervals, with the number of classes determined by the number of data points. This is useful for presenting easy-to-view data that presents logically, but it does not work for all data sets. One example is that lopsided data could present most of the values as the same. Quantile generalizes the data, sacrificing accuracy for simplicity of viewing. This method lumps less common values together for a more even distribution. Natural Break also sacrifices accuracy, but leaves slightly more accuracy. Standard Deviation divides each region into 5 categories, with an even distribution. This removes a lot of detail but shows outliers very easily. Each of these methods have thier own uses depending on the map required, but if used incorrectly, can skew data massively.

Comments
Post a Comment