Bar Chart

A bar chart is a pictorial representation of the information in a frequency distribution. It displays the classes on the horizontal axis and the frequencies or relative frequencies of the classes on the vertical axis. The height of a bar represents how common a particular value or category is in a distribution. A frequency is the number of observations that fall in a class—that is, counts. A relative frequency is the ratio of the frequency of a class to the total number of observations—that is, the proportion or percentage of cases that fall into a class.

One may create either a frequency or a relative frequency bar chart. A frequency bar chart is a graph that displays the classes on the horizontal axis and the frequencies on the vertical axis. The frequency of each class is represented by a vertical bar whose height is equal to the number of times that class occurs in the data set. A relative frequency bar chart is a graph that displays the classes on the horizontal axis and the relative frequencies of the classes on the vertical axis. The only necessary difference between the two types of bar charts is the label on the y-axis: For a frequency bar chart, it will be counts, while for the relative frequency bar chart, it will be percentages.

It is also possible, although less common, to create a horizontal bar chart, which may display either frequency or a relative frequency. A horizontal bar chart displays the classes on the vertical axis and the frequencies or relative frequency on the horizontal axis.

Bar charts are distinguished in two primary ways from histograms:

• 1.
  Bar charts are customarily used for discrete or categorical data, while histograms are used only for quantitative data. When histograms are used for continuous data, it usually needs to be grouped into categories.
• 2.
  In a bar chart, space is left between the bars, that is, they do not touch each other, while in a histogram, bars may be connected to each other without space.

The second rule emphasizes the discrete or categorical nature of the data presented by the bar chart.

Consider the data given in Table 1, which were collected in a survey from a class of 26 students at Columbus State University.

The classes for grouping the data of sex are ‘Male’ and ‘Female,’ while the classes for grouping the data of siblings are numbers from 1 to 5. Tallying the data sets in Tables 2 and 3, we obtain the frequency and relative frequency distributions for sex and siblings, respectively.

A frequency bar chart and relative frequency bar chart for sex and siblings are displayed in Figures 1 and 2.

Figure 1 Number of Male and Female Students in a Class of Students at Columbus State University

Figure 2 Number of Siblings for Students in a Class at Columbus State University

...