Scribd
Upload
47 views10 pages

GEO 426: Choropleth Maps Tanita Suepa 1. Classification Map

This document discusses different classification methods for mapping breast cancer rates and population changes in the United States. It analyzes manual, equal interval, defined interval, standard deviation, and natural breaks classification techniques. For breast cancer rates, the manual classification method produces the best representation of the data distribution. For population changes, standard deviation classification with a diverging color scheme is most suitable since it considers the normal distribution of the data. However, each method has limitations, such as subjective break values for manual or inability to change class numbers for defined interval.

Uploaded by

Aurencio Lozano
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
47 views10 pages

GEO 426: Choropleth Maps Tanita Suepa 1. Classification Map

This document discusses different classification methods for mapping breast cancer rates and population changes in the United States. It analyzes manual, equal interval, defined interval, standard deviation, and natural breaks classification techniques. For breast cancer rates, the manual classification method produces the best representation of the data distribution. For population changes, standard deviation classification with a diverging color scheme is most suitable since it considers the normal distribution of the data. However, each method has limitations, such as subjective break values for manual or inability to change class numbers for defined interval.

Uploaded by

Aurencio Lozano
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 10

GEO 426 : Choropleth Maps Tanita Suepa

1. Classification Map

All of my classification maps use red sequential scheme because the intensity of red can
identify the severity of breast cancer in each area (dark red means to concern about this disease
in that areas) and map users can also compare between different methods by using the same
sequential scheme.

1.1 Manual Classification

This map uses manual classification based on natural breaks which adjusts break
values along natural grouping of data. The result of this classifation provides the best
representation when comparing to the other maps. Logical breaks of this method have positive
affected to data characteristic because it minimize differences between data values in the same
class and maximize differences between classes. The histogram clearly shows that the break
values are placed where there are the gaps between clusters of values, such as the middle group
(group 3, 25-26) has more specific and narrower range than other classes because of the high
number of values and the value differences from other classes; therefore, this range should be
seperated from class 2 and 4. This method produces natural groups that is suitable for this data
and it also deals with outliers. However, the obvious problem of manual method is that break
values can vary among map makers.

1
Figure 1 Manual Classification Map

Figure 2 Histogram of Manual Classification

2
1.2 Equal Interval Classification

This method is easy for map users to intrepret the data. The legend limits contain no
missing value. Nevertheless, this approach fails to represent the distribution of data along the
number of line so some classess have few observations, such as class 1 (15.5-19.5) and class 5
(31.1-35.0) when comparing to other methods.

Figure 3 Equal Interval Classification Map

3
Figure 4 Histogram of Equal Interval Classification

4
1.3 Defined Interval Classification

Defined Interval Classification is a convinent technique to class the data and easy for
map useres to understand the legend because there are only three classes. However, the
limitation of this method is that map makers cannot add more number of classes (the default is 3
classes and cannot change it). With this limitation, this technique does not provide a good
representation of data. As shown in the map, most of US. Area fall in the second class, so map
users cannot distinquish the different of data in each area. The result of this classification is not
appropriate to represent US breast cancer.

Figure 5 Defined Interval Classification Map

5
Figure 6 Histogram of Defined Intervall Classification

6
2. Change Maps

2.1 Standard Deviation Classification

This map uses Standard Deviation Classification with diverging scheme. The diverging
scheme emphasizes on the highest and lowest values that are appropriate for change map and
this scheme is easy to understand the legend. This technique considers the distribution of data
along the number of line, it computes data intervals by using the mean and standard deviation.
The legend of SD classification is no gaps and it represents dividing point and displays a
contrast of values above and below it, as shown in positive and negative classes on the map that
related to the population change from the mean value. The histogram of this data has normal
distribution, so SD classification is suitable for mapping this distribution. However, the
disadvantage is that it works well only with data that are normally distribution and it also requires
some basic statistic to understand map.

Figure 7 Standard Deviation Classification Map

7
Figure 8 Histogram of Standard Deviation Classification

8
2.2 Natural Breaks Classification

This map uses natural breaks with diverging scheme, it is also good to emphasize the
highest and lowest changes. The variety of hues helps distinquish symbol categories that are
classifed in three groups; the first three classes represent the low changes of population, the
middle class shows little change and another three classes show the high changes. The natural
breaks produce variable class width; as a result, class breaks are defined differently.
Nevertheless, natural breaks will show the good result for uneven distribution but this data has
normal distribution so natural break classification is not the best for this particular data.

Figure 9 Natural Breaks Classification Map

9
Figure 10 Histogram of Natural Breaks Classification

10

You might also like