Data presentation for single variable

Welcome to Data Presentation!

In this chapter, we are moving from just looking at piles of numbers to creating "pictures" of data. Statistics is essentially storytelling with numbers, and your job is to make that story clear and accurate. Whether you are looking at the heights of athletes or the number of pets people own, the way you present that data determines how well people understand it. Don't worry if some of the graphs look a bit intimidating at first—we'll break them down step-by-step!

1. The Building Blocks: Types of Data

Before we can draw a graph, we need to know what kind of data we are dealing with. Think of this like choosing the right container for different types of food; you wouldn't put soup in a flat plate!

Categorical Data: These are "labels" or "names." Example: Eye color, favorite pizza topping, or car brand.

Discrete Data: These are "counted" values. They usually have fixed values with no "in-between." Example: The number of siblings you have (you can't have 2.4 siblings!).

Continuous Data: These are "measured" values. They can take any value within a range. Example: Your height, the time it takes to run 100m, or the weight of an apple.

Ranked Data: Data that has a specific order. Example: Finishing positions in a race (1st, 2nd, 3rd).

Quick Review: Always ask yourself, "Am I counting this or measuring it?" Counting usually means Discrete, measuring usually means Continuous.

Key Takeaway: Identifying the data type is the first step in choosing the right graph. You can't draw a histogram for eye colors!

2. Standard Diagrams for Single Variables

There are several ways to show data. Let's look at the most common ones you'll need for your MEI exams.

Vertical Line Charts and Bar Charts

Used for Categorical or Discrete data. Each bar or line represents a category. The height shows the Frequency (how many times it occurs).

Stem-and-Leaf Diagrams

These are great because they show every single piece of data while still looking like a bar chart turned on its side. Example: The numbers 21, 23, 23, 28 would have a 'stem' of 2 and 'leaves' of 1, 3, 3, 8.
Common Mistake Alert: Never forget to include a Key! Without a key (e.g., 2 | 1 means 21), your diagram is just a jumble of numbers.

Pie Charts

Used to show how a "whole" is split into "parts." The angle of each sector is proportional to the frequency. To find the angle: \( \text{Angle} = \frac{\text{Frequency}}{\text{Total Frequency}} \times 360^\circ \).
Did you know? MEI might ask about "Comparative Pie Charts." If you have two pie charts and one represents a larger total population, its Area should be larger than the other one.

Dot Plots

Imagine a bar chart, but instead of a solid bar, you stack dots on top of each other. Each dot represents one piece of data. They are perfect for small datasets where you want to see the individual values clearly.

Key Takeaway: Use Bar/Line charts for discrete data and Stem-and-Leaf when you want to keep the original values visible.

3. Histograms: The Area Rule

Histograms are used for Continuous data that has been grouped into "classes." They look like bar charts, but there is one massive difference: The Area is the Frequency.

Don't let this trip you up! In a standard bar chart, you look at the height. In a histogram, if the bars have different widths, the height alone doesn't tell the whole story.

Frequency Density

To draw a histogram correctly, we use Frequency Density on the vertical axis (the y-axis).
The formula is: \( \text{Frequency Density} = \frac{\text{Frequency}}{\text{Class Width}} \)
This ensures that: \( \text{Area} = \text{Class Width} \times \text{Frequency Density} = \text{Frequency} \).

Step-by-Step for Histograms:
1. Find the Class Width for each group (Upper Boundary - Lower Boundary).
2. Calculate the Frequency Density for each group.
3. Draw your axes, putting Frequency Density on the vertical axis.
4. Draw your bars. Ensure there are no gaps between bars for continuous data!

Encouraging Phrase: If you get stuck, just remember: Width times Height equals how many things are in the box!

Key Takeaway: For histograms, Height = Frequency Density. Area = Frequency.

4. Cumulative Frequency and Box Plots

These two are like best friends; they work together to show the "spread" and "position" of data.

Cumulative Frequency

This is a "running total." You add up the frequencies as you go along. When you plot this, you always plot the cumulative frequency against the Upper Class Boundary. The graph should look like a smooth, stretched-out 'S' shape.

Box-and-Whisker Diagrams (Box Plots)

A box plot summarizes data using five key numbers:
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)

Analogy: Think of a box plot like a summary of a book. It doesn't tell you every word, but it tells you where the story starts, where the middle is, and where the most action (the middle 50% of data) happens.

Key Takeaway: Cumulative frequency helps you find the Median and Quartiles, which you then use to draw your Box Plot.

5. Describing the Shape (Distributions)

When you look at a graph, what is it "doing"? We describe the shape of the distribution using these terms:

Unimodal: It has one clear peak (mode).
Bimodal: It has two clear peaks (like the humps of a camel).
Symmetrical: The left side is a mirror image of the right side.
Skewed: The "tail" of the graph is pulled to one side.

Understanding Skewness

This can be tricky! To remember which is which, look at where the tail is, not the peak.
Positive Skew: The "tail" points to the right (positive direction). Most data is on the left.
Negative Skew: The "tail" points to the left (negative direction). Most data is on the right.

Memory Aid: If you "skew-er" a piece of meat, the long stick is the tail. If the long stick points to the high numbers, it's Positive!

Key Takeaway: Skewness follows the tail. Tail to the right = Positive Skew.

6. Selecting and Critiquing Diagrams

In your exam, you might be asked why one graph is better than another or asked to find a mistake. Use this checklist:

1. Scale: Is the scale consistent and sensible?
2. Labels: Are the axes labeled with units (e.g., "Height / cm")?
3. Appropriateness: Is it a histogram for continuous data or a bar chart for discrete data?
4. Clarity: Does the graph make the data easier to understand, or does it look messy?

Time Series Graphs: If you are looking at data over time (like temperature over a week), use a line graph where time is on the horizontal axis. This helps you spot trends (is it generally going up or down?).

Key Takeaway: A good graph is honest and clear. Always check for labels, units, and the correct diagram type for your data.

Summary Review Box

Discrete Data: Use Bar Charts or Stem-and-Leaf.
Continuous Data: Use Histograms (Area = Frequency).
Running Totals: Use Cumulative Frequency to find Quartiles.
Summarizing Spread: Use Box Plots (Min, \(Q_1\), Median, \(Q_3\), Max).
Skewness: Follow the tail!