A bar graph, like a pie chart, is a common way to present data. In fact, you can take the same dataset from your mammal sighting and trapping study that you presented in a pie chart and present it in a bar graph. Both a pie chart and a bar graph are good choices for discrete data, such as the data from the mammal trapping study, where each species (A-F) is associated with a certain number of sightings.
A bar graph has two axes: the x-axis is the horizontal axis on the bottom, and the y-axis is the vertical axis on the left. The x-axis shows the specific categories being compared, and the y-axis shows the values being measured. Each axis has a label describing what the axis represents, with appropriate units. For example, in a bar graph of your trapping study, the x-axis shows the specific categories you are studying, in this case each species, denoted A-F. The y-axis shows the number of times each species was trapped, indicated by the numbers 0-30. Then, you can represent each species as a bar or column. The height of the bars is proportional to the number of each species trapped, as shown in Figure 4.
What can this bar graph tell you about your data? First, find Species A along the x-axis. The bar that corresponds to Species A is the orange bar directly above it. The top of the bar lines up with the number 17 on the left-hand y-axis, indicating that Species A was trapped 17 times.
Note that, like the pie chart in Figure 3, the bar graph in Figure 4 makes it easy to see the relative number of times each species was trapped. The data are the same in both figures; they are just presented differently. An advantage of a pie chart is that it is easy to see the relative proportions of each category (in this case, species). For example, from a quick glance at the pie chart shown in Figure 3, it is clear that Species A represents about a quarter of all sightings and Species B represents about half of all sightings. This is more difficult to see in the bar graph. An advantage of the bar graph shown in Figure 4, however, is that the species are organized from A-F along the x-axis, so it is easy to find each species and learn about them in order.
You will see many examples of bar graphs in your textbook. Consider this graph from Figure 8.3 Does the oxygen released by photosynthesis come from H2O or CO2? In the experiment discussed in the figure, researchers measured the percent of 18O2 (oxygen gas containing an isotope of oxygen) at the start (initial) and end (final) of the experiment.
The bar graph shows the two time points (initial and final) along the horizontal x-axis and the percent 18O2 along the vertical y-axis. This kind of graph makes it very clear that the percent 18O2 was higher at the end of the experiment than it was at the beginning of the experiment. This is the key observation that led the researchers to the conclusion that the oxygen in photosynthesis comes from H2O and not CO2, and the bar graph presents the data clearly and effectively.
Both pie charts and bar graphs are useful for discrete data. What about continuous data? Imagine you collect data about the body lengths of the mammals you trapped. Body lengths are an example of continuous data because they can take on any value within a certain range. A histogram is a good option for displaying continuous data. A histogram is a diagram consisting of rectangles whose areas are proportional to the frequency of a variable and whose widths are equal to the class interval.
A histogram looks similar to a bar graph because, in both cases, they show bars of different heights. However, there is a key difference between a histogram and a bar graph. In a bar graph, discrete categories (different species) are along the x-axis, and the columns in the bar graph have gaps between them, as you can see in Figure 4. In a histogram, by contrast, there is a continuous sequence of data, in this case representing body lengths. To organize these data, you can impose your own categories, such as 1-20 cm, 21-40 cm, 41-60 cm, and so on, and place these on the x-axis. As a result, there are no gaps between the columns because the end of one range (1–20 cm) is continuous with the beginning of the next (21–40 cm), as shown in Figure 5.