Welcome to Data Visualization!

In the world of statistics, numbers can sometimes feel like a messy pile of bricks. Presentation is the art of building something meaningful out of those bricks so we can see the "shape" of the data. In this chapter, we will learn how to use histograms, cumulative frequency graphs, and box plots to turn raw data into clear stories.

Whether you are at SL or HL, these tools are essential for Paper 1 (by hand) and Paper 2 (using your GDC). Let’s dive in!

1. Histograms

A histogram is used to represent continuous data (things we measure, like height, time, or weight). At first glance, it looks like a bar chart, but there are two very important differences:

1. There are no gaps between the bars (because the data is continuous).
2. The horizontal axis represents the class intervals (the groups).

Key Features to Remember:

  • The x-axis shows the variable you are measuring (e.g., \(0 \le x < 10\)).
  • The y-axis shows the frequency (how many items fall into that group).
  • Important Note: For the IB AA course, you are not required to learn frequency density histograms. This means the height of the bar simply represents the frequency!

Quick Tip: If a question asks you to identify the modal class from a histogram, just look for the tallest bar!

2. Cumulative Frequency

The word "cumulative" means "adding up as you go." Think of it like a "running total."

How to Build a Cumulative Frequency Table:

Imagine you have data for test scores. To find the cumulative frequency for a specific group, you add the frequency of that group to the sum of all the groups before it.

Example:
Group 0-10: Frequency \(5\) \(\implies\) Cum. Freq. \(5\)
Group 10-20: Frequency \(8\) \(\implies\) Cum. Freq. \(5 + 8 = 13\)
Group 20-30: Frequency \(10\) \(\implies\) Cum. Freq. \(13 + 10 = 23\)

The Cumulative Frequency Graph (The "S-Curve"):

When plotting this graph, always plot the cumulative frequency against the upper class boundary. For example, if your group is \(10 \le x < 20\), you plot the point at \(x = 20\).

We connect the points with a smooth curve that looks like a stretched-out letter 'S'.

Finding Key Values from the Graph:

The main reason we draw these graphs is to find quartiles and percentiles:

  • The Median (\(Q_2\)): Go to \(50\%\) of the total frequency on the y-axis, move across to the curve, and drop down to the x-axis.
  • Lower Quartile (\(Q_1\)): Go to \(25\%\) of the total frequency.
  • Upper Quartile (\(Q_3\)): Go to \(75\%\) of the total frequency.
  • Percentiles: For the \(k^{th}\) percentile, go to \(k\%\) of the total frequency. For example, the \(90^{th}\) percentile is the value that \(90\%\) of the data is below.

Key Takeaway: Cumulative frequency graphs are all about finding "where a certain percentage of the data sits."

3. Box and Whisker Diagrams

A box and whisker diagram (often just called a box plot) is a visual summary of the "Five-Number Summary" of a data set.

The Five-Number Summary:

1. Minimum value (the start of the left whisker)
2. Lower Quartile (\(Q_1\)) (the start of the box)
3. Median (\(Q_2\)) (the line inside the box)
4. Upper Quartile (\(Q_3\)) (the end of the box)
5. Maximum value (the end of the right whisker)

Measures of Spread:

From a box plot, you can easily see two important measures of spread (which are covered more deeply in the Measures of Central Tendency and Dispersion chapter):

  • Range: \(Maximum - Minimum\)
  • Interquartile Range (IQR): \(Q_3 - Q_1\) (this represents the width of the box and shows where the middle \(50\%\) of the data lies).

Outliers:

Sometimes, data points are so far away from the rest that they are considered outliers. In the IB syllabus, a common boundary for an outlier is any value that is:

Smaller than \(Q_1 - 1.5 \times IQR\)
OR
Larger than \(Q_3 + 1.5 \times IQR\)

On a diagram, outliers are usually marked with an 'x' or a dot beyond the whiskers.

Did you know? The box plot is great for comparing two sets of data. If you draw two box plots on the same scale, you can instantly see which group has a higher median or which group is more "spread out."

4. Summary Table: Choosing the Right Tool

Don't worry if you aren't sure which graph to use; here is a quick guide:

Histogram: Best for seeing the shape of the distribution (Is it symmetrical? Is it skewed?).
Cumulative Frequency: Best for finding percentiles and specific cutoff scores.
Box Plot: Best for comparing different data sets and spotting outliers.

5. Common Mistakes to Avoid

  • Plotting at the midpoint: For cumulative frequency graphs, always plot at the upper boundary of the interval, not the middle! (Histograms use boundaries too, but the bar covers the whole width).
  • Y-axis confusion: On a cumulative frequency graph, the y-axis is the running total, not the individual frequency of each group.
  • Calculator Notation: If you use your GDC to find these values, remember to write them down using standard mathematical notation in your exam.
  • Missing Labels: Always label your axes. If the x-axis is "Time (seconds)," make sure that is written clearly.

Quick Review:
Can you find the \(IQR\) if you know \(Q_1\) and \(Q_3\)? Yes! It is \(Q_3 - Q_1\).
Can you find the median from a histogram? You can estimate which class it falls in, but a cumulative frequency graph gives you a more precise estimate!