horizontal axis to display the relative position of each data point. As an exam-
ple, Figure 2.1 depicts the crude death rates for all 50 states and the District of
Columbia, from a low of 393.9 per 100,000 population to a high of 1242.1 per
100,000 population. An advantage of a one-way scatter plot is that since each
observation is represented individually, no information is lost; a disadvantage
is that it may be di‰cult to read (and to construct) if values are close to each
other.
2.1.2 Frequency Distribution
There is no di‰culty if the data set is small, for we can arrange those few
numbers and write them, say, in increasing order; the result would be su‰-
ciently clear; Figure 2.1 is an example. For fairly large data sets, a useful device
for summarization is the formation of afrequency tableorfrequency distribu-
tion. This is a table showing the number of observations, calledfrequency,
within certain ranges of values of the variable under investigation. For exam-
ple, taking the variable to be the age at death, we have the following example;
the second column of the table provides the frequencies.
Example 2.1 Table 2.1 gives the number of deaths by age for the state of
Minnesota in 1987.
Figure 2.1 Crude death rates for the United States, 1988.TABLE 2.1
Age Number of Deaths
< 1 564
1–4 86
5–14 127
15–24 490
25–34 667
35–44 806
45–54 1,425
55–64 3,511
65–74 6,932
75–84 10,101
85 þ 9,825
Total 34,52458 DESCRIPTIVE METHODS FOR CONTINUOUS DATA