Mathfolis

Describing the Distribution of a Quantitative Variable

Unit 1 · Exploring One-Variable Data

What AP Stats asks here

AP Statistics opens with a single recurring framework for quantitative distributions: SOCS — Shape, Outliers, Center, Spread. Almost every Unit 1 free-response prompt and most multiple-choice items on this topic test whether you describe all four in context. Naming the skew by the tail (not the bulk) and matching the center/spread choice to the shape are the two most common AP exam discriminators on this topic.

SOCS

Shape
symmetric, skewed-left, skewed-right, uniform, bimodal\text{symmetric, skewed-left, skewed-right, uniform, bimodal}
Outliers
values unusually far from the rest\text{values unusually far from the rest}
Center
mean xˉ   or   median\text{mean } \bar{x} \;\text{ or }\; \text{median}
Spread
range, IQR, or standard deviation s\text{range, IQR, or standard deviation } s

Skew and the mean–median relationship

Left-skewed (tail on left)
xˉ<median\bar{x} < \text{median}
Symmetric
xˉ≈median\bar{x} \approx \text{median}
Right-skewed (tail on right)
xˉ>median\bar{x} > \text{median}

Choosing the summary pair

Symmetric, no outliers
report mean and standard deviation\text{report mean and standard deviation}
Skewed or contains outliers
report median and IQR (resistant)\text{report median and IQR (resistant)}
AP Tip: Tie every SOCS piece to context. "The distribution is right-skewed" loses points without "...because most home prices cluster near $300K with a long tail toward $2.4M." AP graders reward context-anchored descriptions.
Caution: Skew is named for the direction of the tail, not the bulk. A histogram with the peak on the right and a tail extending left is left-skewed — even though most data sits on the right.
AP Tip: When comparing two distributions, use comparison language ("A is more variable than B") rather than describing each separately. AP rubrics specifically require comparative phrasing.
Type 1

Shape identification

Look at how the data is arranged: where the peak sits, which direction (if any) the tail extends, and whether there is more than one mode. Name shape by the tail, not the bulk.

Example 1
A histogram of starting salaries for 200 college graduates shows the peak at 50,000–50,000–55,000, with frequencies decreasing steadily up to $120,000+ and no values below $30,000. Which best describes the shape of this distribution? (A) Symmetric, because the peak is well-defined (B) Left-skewed, because the bulk is on the right end (C) Right-skewed, because the tail extends toward higher salaries (D) Bimodal, because both low and high earners are represented

Practice more of this type— AI-generated · always-new problems

Generate Problems →
Type 2

Full SOCS description

Given summary information about a quantitative distribution, write (or pick) a description that names all four SOCS pieces in context and chooses the appropriate center/spread pair for the shape.

Example 2
A histogram of home prices in a neighborhood (n=80n = 80) shows: range 120,000to120,000 to2,400,000, peak at 300K–300K–400K, mean 520,000,median520,000, median380,000. A few homes are priced above $1,500,000. Which choice best describes the distribution? (A) Symmetric distribution with a mean of $520K; report mean and standard deviation. (B) Right-skewed with a few high outliers above 1.5M;median(1.5M; median (380K) is the better center because the mean is pulled up by the expensive homes. (C) Left-skewed because most homes cluster at the low end of the price range; report mean ($520K) and range. (D) Bimodal because mean and median differ; report both mean and median with no preference.

Practice more of this type— AI-generated · always-new problems

Generate Problems →
Type 3

Comparing two distributions

When comparing two groups, use comparison language. Lead with the more distinguishing SOCS piece — often spread — and tie every comparison to the variable being measured.

Example 3
Side-by-side boxplots show test scores for two classes: Class A: Min 60, Q1 75, Median 82, Q3 88, Max 95 Class B: Min 45, Q1 65, Median 80, Q3 90, Max 99 Which choice best compares the two distributions? (A) Both classes are symmetric and have the same median, so the distributions are essentially identical. (B) Class A has a higher median (82) than Class B (80) and is much more variable (IQR 25 vs 13). (C) The medians are similar (~80–82), but Class B is more variable than Class A (IQR 25 vs 13) and slightly right-skewed, while Class A is more tightly clustered. (D) Class B has a higher maximum, so Class B is the stronger class overall.

Practice more of this type— AI-generated · always-new problems

Generate Problems →