To describe the distribution of a quantitative variable, check four things: shape, center, variability (spread), and any unusual features like outliers, gaps, or clusters. Always describe these in the context of the variable and its units, and remember that describing a sample does not let you make claims about a whole population.
Why This Matters for the AP Statistics Exam
Describing distributions is a core skill you will use all year, starting in Unit 1 and continuing into comparing groups, checking conditions for inference, and reading computer output. On the exam, you may be asked to describe what a histogram, dotplot, stemplot, or boxplot shows. A complete answer covers shape, center, variability, and unusual features in context. A response that only mentions the center, for example, is considered incomplete.
This topic builds the language you need to talk about data clearly. Later topics give you the exact calculations for center and spread, but the habit of naming shape, center, variability, and unusual features starts here.
Key Takeaways
- A full description includes shape, center, variability (spread), and unusual features such as outliers, gaps, clusters, or multiple peaks.
- Shape covers symmetry vs. skew and the number of peaks (unimodal, bimodal, or approximately uniform).
- A distribution is skewed right if the right tail is longer and skewed left if the left tail is longer. Symmetric means the two halves are near mirror images.
- Outliers are points unusually small or large compared to the rest of the data. Gaps are empty regions, and clusters are concentrations of data usually separated by gaps.
- Always describe the distribution in context, including the variable and its units.
- Describing one data set does not let you claim those properties hold for a larger population. It can only suggest ideas to test later.
The Four Things to Describe
When you describe a quantitative distribution, cover shape, center, variability, and unusual features. A common memory trick is SOCS (Shape, Outliers, Center, Spread) or CUSS, but the acronym only helps if you actually explain each part.
Shape
Shape describes the overall form of the distribution.
Symmetry. A distribution is symmetric if the left half is roughly a mirror image of the right half. If you could fold the graph down the middle, the two sides would line up closely. A bell-shaped curve is the classic symmetric example. Real data is rarely perfectly symmetric, so "approximately symmetric" is usually the honest description.
Skewness. A distribution is skewed to the right (positive skew) if the right tail is longer than the left. It is skewed to the left (negative skew) if the left tail is longer than the right. The direction of skew is named for the longer tail, not where most of the data sits.
Peaks (modes). Count the prominent peaks:
- Unimodal: one main peak
- Bimodal: two prominent peaks
- Approximately uniform: bar heights are about the same with no prominent peak
Two clear peaks can hint that the data combines two different groups.
Unusual Features
After shape, point out anything that stands out.
Outliers. Outliers are data points that are unusually small or large relative to the rest of the data. Mention them when you see them, because they can pull on certain summaries of center and spread. Do not automatically throw them out; note them and describe them.
Gaps. A gap is a region between two data values where there are no observed data. Gaps can signal separate groups within the data.
Clusters. Clusters are concentrations of data, usually separated by gaps. Naming clusters helps describe data that splits into distinct groups.
Center
Center answers "what is a typical value?" The two common measures of center are the mean (the average) and the median (the middle value when data are ordered). In a roughly symmetric distribution the mean and median are close. In a skewed distribution they can differ, which is why you should match your choice of center to the shape. The exact formulas and how to compute these come in the next topic.
Variability (Spread)
Variability describes how spread out the data is. Reporting a center without a measure of spread gives an incomplete picture. Common ways to measure spread include the range, the interquartile range (IQR), and the standard deviation. The calculations for each come in later topics, but here the goal is to recognize that spread is part of a complete description.
How to Use This on the AP Statistics Exam
Free Response
When a question shows a graph of quantitative data and asks you to describe it, write about shape, center, variability, and any unusual features, all in context.
- Name the shape (symmetric, skewed right, skewed left) and the number of peaks.
- Give a sense of center and a sense of spread using the variable's units.
- Point out outliers, gaps, or clusters if they appear.
- Tie every statement to the actual variable, such as "the test scores are skewed right," not just "it is skewed right."
A response that only addresses center is incomplete. Make sure you hit each piece.
MCQ
Multiple-choice questions often show a histogram, dotplot, stemplot, or boxplot and ask you to identify the shape, spot an outlier, or match a graph to a description. Read the axis labels and scales carefully before choosing. Watch for skew direction, since the longer tail names the skew.
Common Trap
When two distributions are compared, you have to actually compare them, using words like "greater than" or "more spread out than," not just describe each one separately. That comparison skill builds on the describing skill from this topic.
Common Misconceptions
- Skew is named for the longer tail, not the cluster of data. Right skew means the long tail points right, even though most values sit on the left.
- Describing only the center is incomplete. You must also give shape, variability, and unusual features for a full answer.
- Symmetric does not mean perfectly symmetric. Most real data is only approximately symmetric, and that is fine to say.
- Outliers are not automatically errors. They are unusual values, but you should note and describe them rather than deleting them by default.
- Describing a data set is not the same as a claim about a population. Descriptive statistics summarize the data you have. They can suggest ideas to test later, but they do not prove anything about a larger group.
- Uniform is a shape, not "no shape." Approximately uniform means bar heights are about equal, with no prominent peak.
- Forgetting context loses meaning. Always mention the variable and its units when describing a distribution.
Related AP Statistics Guides
- Unit 1 Overview: Exploring One-Variable Data
- 1.1 Introducing Statistics: What Can We Learn from Data?
- 1.3 Representing a Categorical Variable with Tables
- 1.8 Graphical Representations of Summary Statistics
- 1.9 Comparing Distributions of a Quantitative Variable
- 1.4 Representing a Categorical Variable with Graphs
Vocabulary
The following words are mentioned explicitly in the College Board Course and Exam Description for this topic.Term | Definition |
|---|---|
bimodal | A distribution with two prominent peaks. |
center | A measure indicating the middle or typical value of a distribution. |
cluster | Concentrations of data usually separated by gaps in a distribution. |
descriptive statistics | Methods used to summarize and describe the characteristics of a data set without making inferences about a larger population. |
distribution | The pattern of how data values are spread or arranged across a range. |
gap | Regions of a distribution between two data values where there are no observed data. |
outlier | Data points that are unusually small or large relative to the rest of the data. |
quantitative data | Data that consists of numerical values that can be measured and analyzed mathematically. |
shape | The overall form or pattern of a distribution, including characteristics like skewness and modality. |
skewed left | A distribution with a longer tail extending to the left, where the mean is typically less than the median. |
skewed right | A distribution with a longer tail extending to the right, where the mean is typically greater than the median. |
symmetric | A distribution where the left half is the mirror image of the right half. |
uniform | A distribution where each bar height is approximately the same with no prominent peaks. |
unimodal | A distribution with one main peak. |
variability | The spread or dispersion of data values in a distribution. |
Frequently Asked Questions
What is AP Statistics 1.6 about?
AP Statistics 1.6 is about describing the distribution of a quantitative variable. A complete description includes shape, center, variability, and unusual features such as outliers, gaps, clusters, or multiple peaks, all in context.
How do I describe a distribution in AP Statistics?
Describe shape, center, variability, and unusual features. Use context and units, such as describing the distribution of test scores or response times rather than only saying that the graph is skewed or spread out.
What does SOCS mean in AP Statistics?
SOCS is a memory tool for Shape, Outliers, Center, and Spread. It helps you remember the main parts of a distribution description, but your final answer should use context and mention gaps, clusters, or multiple peaks when they appear.
How do I tell if a distribution is skewed left or right?
A distribution is skewed right if the right tail is longer and skewed left if the left tail is longer. Name the skew by the direction of the longer tail, not by the side where most data values are clustered.
What are gaps and clusters in a distribution?
A gap is a region of a distribution where no data values appear. A cluster is a concentration of data values, often separated from another cluster by a gap. Both are unusual features worth mentioning in a complete description.
How should I answer distribution-description questions on the AP Stats exam?
Write a sentence or two that covers shape, center, variability, and unusual features in context. If comparing two distributions, use direct comparison words like greater, smaller, more variable, or less spread out instead of describing each graph separately.