01 / 21

Graphical Representations
of Summary Statistics

Learn how to visualize center, spread, and shape using dotplots, histograms, boxplots, and stemplots: the key to reading data at a glance.

AP Statistics

What Are Summary Statistics?

Summary statistics are single numbers that describe key features of a dataset. They fall into three categories: measures of center, measures of spread, and measures of position.

Center
Mean \(\bar{x}\), median, mode: where the "middle" of the data lies
Spread
Range, IQR, standard deviation \(s\): how much the data varies
Position
Quartiles \(Q_1, Q_3\), percentiles, min/max: where individual values fall

Why Graphs Matter

A table of numbers can hide important patterns. Graphs let you see shape, outliers, and clusters instantly. Two datasets can share the same mean and standard deviation yet look completely different when plotted.

The Four Core Graphs

Dotplot
One dot per observation on a number line. Best for small datasets.
Histogram
Bars show frequency in equal-width bins. Best for shape and distribution.
Boxplot
Five-number summary displayed visually. Best for comparing groups and spotting outliers.
Stemplot
Stems and leaves show each value. Best for small-to-medium datasets retaining individual data.

The Boxplot and Five-Number Summary

A boxplot (box-and-whisker plot) displays the five-number summary: minimum, \(Q_1\), median, \(Q_3\), and maximum. The box spans the interquartile range \(\text{IQR} = Q_3 - Q_1\), and whiskers extend to the smallest and largest non-outlier values.

10 20 30 40 50 60
\(\text{Min} = 12\)
\(Q_1 = 22\)
\(\text{Median} = 32\)
\(Q_3 = 45\)
\(\text{Max} = 56\)
\(\text{IQR} = 23\)

Identifying Outliers: the \(1.5 \times \text{IQR}\) Rule

An observation is a potential outlier if it falls more than \(1.5 \times \text{IQR}\) below \(Q_1\) or above \(Q_3\). On a modified boxplot, whiskers stop at the most extreme non-outlier values and outliers are marked individually.

Histograms: Shape and Density

A histogram groups data into equal-width bins and uses bar heights to represent frequency (or relative frequency). The shape tells us about symmetry, skewness, and modality.

0 2 4 6 8 10-20 20-30 30-40 40-50 50-60 60-70 70-80 Right-skewed: tail stretches right

Mean vs. Median and Skewness

The relationship between the mean \(\bar{x}\) and the median reveals the direction of skew. Outliers pull the mean toward the tail but leave the median largely unchanged.

Right-Skewed
\(\bar{x} > \text{median}\). The mean is pulled toward the long right tail.
Symmetric
\(\bar{x} \approx \text{median}\). Center measures nearly equal.
Left-Skewed
\(\bar{x} < \text{median}\). The mean is pulled toward the long left tail.

Dotplots and Stemplots

Dotplots place one dot per observation above a number line. Stemplots (stem-and-leaf plots) split each value into a stem (leading digit) and leaf (trailing digit), preserving every individual data point.

Dotplot 1 2 3 4 5 6 Stemplot Stem Leaf 1 2 5 2 0 3 3 7 3 1 4 6 8 8 4 2 5 5 1 Key: 3|4 = 34

Describing Distributions: SOCS

When the AP exam asks you to describe a distribution, use the SOCS framework. Every complete answer addresses all four elements:

S
Shape: Is the distribution symmetric, left-skewed, right-skewed, uniform, or bimodal?
O
Outliers: Are there any unusual values? Use the \(1.5 \times \text{IQR}\) rule or visual inspection.
C
Center: Estimate the mean or median from the graph. Use median for skewed data.
S
Spread: Report the range, IQR, or standard deviation. State units and context.

How to Read a Boxplot Step-by-Step

1
Identify the five-number summary: read Min, \(Q_1\), Median, \(Q_3\), Max from the plot.
2
Calculate the IQR: \(\text{IQR} = Q_3 - Q_1\). This is the width of the box.
3
Check for outliers: Look for individual dots beyond the whiskers. Verify with fences: \(Q_1 - 1.5 \times \text{IQR}\) and \(Q_3 + 1.5 \times \text{IQR}\).
4
Assess shape: If the median line is centered in the box and whiskers are roughly equal, the distribution is approximately symmetric. Otherwise, it is skewed toward the longer whisker/tail.
5
Describe in context: Always reference the variable and units. "The distribution of test scores is right-skewed with a median of 32 points."

Example 1: Reading a Histogram

A class of 25 students recorded their weekly study hours. The histogram below summarizes the data. Describe the distribution.

0 3 6 9 12 0-2 2-4 4-6 6-8 8-10 10-12 12-14 Weekly Study Hours

Example 2: Comparing Side-by-Side Boxplots

Two classes took the same exam. Compare their performance using the boxplots below.

40 50 60 70 80 90 Class A Class B Exam Score

Example 3: Outlier Effect on Summary Statistics

Consider the dataset: 10, 12, 13, 14, 15, 15, 16, 17, 18, 50. How does the outlier 50 affect the mean and median?

With Outlier
Mean: \(\bar{x} = \frac{180}{10} = 18.0\)
Median: \(\frac{15+15}{2} = 15.0\)
Without Outlier
Mean: \(\bar{x} = \frac{130}{9} \approx 14.4\)
Median: \(15.0\)

Common Mistakes

✕ Confusing Bars and Bins
Reading the height of a histogram bar as an individual data value instead of a frequency count.
✕ Ignoring Context
Describing shape without referencing the variable name and units: "it's right-skewed" instead of "the distribution of test scores is right-skewed."
✕ Using Mean for Skewed Data
Reporting the mean as the "typical" value for a heavily skewed distribution where the median is more appropriate.

Comparing Graphical Displays

Dotplot Histogram Boxplot Stemplot
Best for Small datasets Shape of distribution Comparing groups Retaining values
Shows individual values? Yes No No Yes
Shows shape? Yes Yes Limited Yes
Shows outliers? Yes Somewhat Yes Yes
Easy to compare groups? Moderate Moderate Best Back-to-back

Question 1 of 5

A histogram of household incomes in a city is strongly right-skewed. Which measure of center best represents a "typical" income?

Question 2 of 5

A boxplot shows \(Q_1 = 20\), \(Q_3 = 40\), and \(\text{IQR} = 20\). According to the \(1.5 \times \text{IQR}\) rule, what is the upper fence?

Question 3 of 5

In a distribution where \(\bar{x} = 52\) and the median is 58, the distribution is most likely:

Question 4 of 5

Which graphical display is best for comparing the distributions of exam scores across four different classes?

Question 5 of 5

A stemplot of 15 test scores has the following stems: 6, 7, 8, 9. The stem 7 has leaves 2, 3, 5, 5, 8. How many scores are in the 70s?