You're familiar with bar charts, where the height of each bar shows its frequency. This works perfectly when every category is the same size. But what happens when you're dealing with grouped, continuous data where the groups, or 'classes', have different widths? A tall, narrow bar might actually represent fewer data points than a short, wide one.

Imagine two groups of people who ran a race. Group A contains 10 people who finished in a 5-minute window (e.g., 20-25 minutes). Group B has 12 people who finished in a 15-minute window (e.g., 25-40 minutes). If you just plot the frequency, Group B's bar would be taller, suggesting a more popular finishing time. But that's misleading. The runners in Group A are more densely packed together in time.

To create a fair visual comparison for grouped data with unequal intervals, we use a special type of chart called a histogram. In a histogram, it’s the area of the bar that represents the frequency, not the height.

This simple rule fixes the problem. A group that is twice as wide must have its bar height adjusted so the total area still accurately reflects its frequency. To do this, we calculate a value called frequency density.

The class width is simply the difference between the upper and lower boundaries of a group. Let's look at an example. The table below shows the time taken for a group of students to complete a puzzle.

Notice how the second group (10-15 seconds) has the highest frequency density. Although the third group (15-25 seconds) has the most students (40), they are more spread out. The frequency density of 6.0 for the 10-15 second group tells us this is the most concentrated cluster of results. When we draw the histogram, this bar will be the tallest, giving us a true picture of the distribution.