Choropleth map

A choropleth map is a specific type of statistical thematic map.

It uses pseudocolor to represent an aggregate summary of a geographic characteristic. This characteristic is measured within specific spatial enumeration units. These units are often called districts. They can be large areas like countries or provinces. They can also be smaller areas like counties or census tracts. These maps are vital for visualizing how a variable changes across a geographic area. They also help show the level of variability within a specific region. Because most statistical data is already organized into known geographic units, these maps are very common.

To create a choropleth map, a cartographer must combine two distinct datasets. The first dataset is spatial data. This data provides a partition of geographic space into distinct districts. The second dataset is statistical data. This data represents a variable that has been aggregated within each district. There are two ways to view the relationship between these datasets. The first is the district dominant model. In this view, the districts are the primary focus. Various attributes are collected for each existing governmental unit. The second is the variable dominant model. Here, the focus is on the variable as a geographic phenomenon. The partitioning into districts is simply a convenient way to measure it.

Geographically, the districts used in these maps are usually pre-defined entities. These might be administrative units like states or countries. They might also be districts created specifically for statistical aggregation. Because these boundaries are set before the data is applied, they may not match the actual pattern of the variable. This is a major difference between choropleth maps and isarithmic maps. An isarithmic map uses boundaries drawn according to the pattern of the variable itself.

Using pre-defined regions has several practical advantages. It makes the data easier to compile using GIS or spreadsheets. It also makes the districts easily recognizable to the reader. This allows the information to be used for policy decisions tied to specific districts, such as election results.

Despite these advantages, choropleth maps can lead to misinterpretations. A constant color is applied to an entire district. This makes the district look homogeneous, or the same throughout. In reality, there may be significant variation inside that district. For example, a single city might contain wealthy and poor neighborhoods. However, the map might color the whole city with one "moderate" shade. This can lead to the ecological fallacy or the modifiable areal unit problem (MAUP). These issues occur when real-world patterns do not match the regional units. To reduce these errors, cartographers can use smaller districts. Smaller districts show finer variations, but they can also make a map look overly complex.

The history of these maps is quite long. The earliest known choropleth map was created in 1826 by Baron Pierre Charles Dupin.

He used it to show the availability of basic education in France by department. Soon after, other "tinted maps" appeared in France. These maps visualized "moral statistics" like crime, disease, and living conditions. The popularity of these maps grew alongside national Censuses. For example, Ireland published choropleth maps in its 1841 Census reports. Color became more common after 1850 due to chromolithography. The specific term "choropleth map" was introduced in 1938 by geographer John Kirtland Wright.

Data types are very important when choosing how to map a variable. Variables can be spatially extensive or spatially intensive. An extensive variable is a global property. It applies to an entire district, such as a total population count. Mapping these is generally discouraged because it can be misleading. A large district with a high total population might look more significant than a small, crowded district.

Instead, choropleth maps are best suited for spatially intensive variables. These are also called fields or statistical surfaces. These variables represent properties that could be measured at any location, like density or proportions.

An example is the fraction of Australians identifying as Anglican.

To make intensive variables work correctly, cartographers use a technique called normalization.

Normalization derives an intensive variable from one or more extensive variables. This is often done by calculating a ratio. A common example is calculating population density by dividing total population by total area. This prevents large geographic areas from appearing more dominant simply because they are big.

Without normalization, a map might incorrectly suggest that a large, empty territory is more urbanized than a small, dense one. By using normalized data, the map provides a more accurate view of the underlying phenomenon. This allows us to see clear patterns in human and natural systems, such as wealth or agriculture.