Four types of data classification were highlighted in this lab, each influencing the data differently. The image above shows four maps, each utilising a different classification method for the same data on a map of Vancouver.
Using natural breaks reflects the underlying data distribution. This method maximizes differences across groups and minimizes differences within. Data represented in this manner is very raw and allows for an un-altered interpretation of the data.
Equal interval classification places boundaries at regular intervals between classes. Using this method allows for an easy to interpret map. However, it does not account for data distribution. This could lead to overloaded, or empty classes.
Standard deviation is useful for showing above and below average values on a map. This is due to the fact the classes are centered around the mean value of the data set.
Manual classification involves setting boundaries according to external criteria. This obscures the distribution of the data but can be useful to identify specific regions in question depending on what the cartographer wants to present. This leads to a tailored interpretation of the map.
