Dot Plots and Bar Charts

Students use the options on CODAP’s Configuration and Measure menus to produce displays of the Animals Dataset.

Today’s lesson is all about producing displays in CODAP.

We’ll walk through some of the basic mechanics of creating a display - and then you will have the opportunity to independently create and explore displays in CODAP.

Until we assign variables for the axes, the data points are randomly distributed on the graph.

Hovering over an orange dot reveals the name of that particular animal. Selecting a particular dot causes the table row for that animal to be highlighted in blue. Holding the shift button allows students to select multiple dots in the graphical display, or multiple rows in the table.

When we select a table row (or multiple table rows), the corresponding dots change color. When we set aside selected and / or un-selected cases (by using the "eye" icon), we can temporarily alter the amount of pets in the dataset (with the option to restore to the original dataset).

We can also resize the window by dragging its borders.

Once we have a graph of randomly distributed data points, we can organize the data by selecting attributes from our table that we want to appear on the axes of our graph.

Dot plots and bar charts look pretty similar. Why would we opt to use one over the other?

Dot plots are best for smaller datasets. If we anticipate that there will be fewer than about 10 rows per category, a dot plot works well. We will be able to clearly, easily identify the number of dots in each category, even though there are no values or intervals on the y-axis.

Bar charts work well for large datasets. It would be very inconvenient to draw a display with five million dots! If we opt to use a bar chart rather than a dot plot, we can simply adjust the intervals on the y-axis to meet our needs. For instance, we could determine that a one-centimeter bar represents one million rows of our dataset.

The image below shows a dot plot for a large dataset next to a dot plot for a small dataset. The difference between the bars for the small dataset is easy to see, but the difference for the large dataset is difficult to read at a glance.

Bar charts and dot plots display how much of the sample belongs to each category. If they are based on sample data from a larger population, we use them to infer the proportion of a whole population that might belong to each category.

While bars in bar charts should follow some logical order (alphabetical, small-medium-large, etc), they can technically be placed in any order, without changing the meaning of the chart.

Categorical data is used to classify, rather than to measure. Only when data is being treated categorically will you be invited to fuse data points - transforming a dot plot into a bar chart. Quantitative (or numeric) data must measure or compare; it is subject to the laws of arithmetic.

Bar charts look a lot like another kind of display - called a "histogram" - which displays numeric data, not categorical.

Creating each of these displays begins the same way: we create a dot plot, and then modify it using CODAP’s menus. Depending on what type of data the dot plot displays, we can transform it into either a bar chart (for categorical data), or a histogram (for numeric data). These displays serve unique purposes!

Pie charts display categorical data, too, but CODAP doesn’t offer them largely because many find them challenging to read.

Students learn how to create groups within groups, showing the relative frequency of one variable across values of another variable using stacked and multi bar charts.

Comparing groups is great, but sometimes we want to compare sub-groups across groups. In this example, we want to compare the distribution of sexes across each species.

CODAP allows us to build a variety of displays where we specify both a group and a subgroup.

All of the charts we’ve looked at in this lesson work with categorical data, showing us the frequency of values in one or two groups.

Students explore the CODAP data display options available to them. In doing so, they experiment with new charts and get comfortable with CODAP as a platform for doing data science.

There are lots of different kinds of charts and plots that we can build in CODAP!

CODAP is designed to be student-friendly! Its interface encourages guesswork…​ but we can save some time by being a bit more strategic.

Let’s try a more methodical approach to creating displays.

There are many possible misconceptions about displays that students may encounter here. But that’s OK! Understanding all those other plots is not a learning goal for this lesson. Rather, the goal at this stage is to have them build familiarity and confidence with the CODAP tool and how it makes data displays.

Today you’ve added more data displays to your toolbox. You can create dot plots and bar charts to visually display categorical data, and you’ve developed a general approach to guide you as you create other displays.