AP Statistics describing distributions cheat sheet

By Jude Wallis · Published

Describe a quantitative distribution by its shape, center, variability, and unusual features, in context with units. Use the mean and standard deviation for roughly symmetric data and the median and IQR for skewed data or data with outliers.

AP Statistics: Unit 1 (topics 1.6 Descriptions for One Quantitative Variable Distributions, 1.7 Summary Statistics for One Quantitative Variable, 1.8 Graphical Representations of Summary Statistics for One Quantitative Variable, 1.9 Comparisons of the Distributions for One Quantitative Variable). Describing and comparing distributions of one quantitative variable is Unit 1, topics 1.6 through 1.9, of the Fall 2026 AP Statistics course. Quartiles here use the median-excluded convention.

The four things to describe

FeatureWhat to stateWords to use
ShapeSkewness or symmetry, and the number of peaksSkewed right, skewed left, approximately symmetric; unimodal, bimodal, approximately uniform
CenterA typical value, with unitsMedian or mean
VariabilityHow spread out the values are, with unitsRange, IQR, or standard deviation
Unusual featuresAnything that departs from the overall patternOutliers, gaps, clusters

Every part of the description names the variable and its units. "The distribution of commute times is skewed right with a median of 19 minutes" is a description. "It is skewed right with a median of 19" is missing the context. A longer treatment is in how to describe a distribution.

Shape vocabulary

ShapeWhat the graph looks likeMean compared with median
Skewed rightThe tail toward larger values is longerMean is usually larger than the median
Skewed leftThe tail toward smaller values is longerMean is usually smaller than the median
Approximately symmetricThe left half is roughly a mirror image of the right halfMean and median are close

Skew is named for the side with the longer tail.

PeaksMeaning
UnimodalOne main peak
BimodalTwo prominent peaks
Approximately uniformNo prominent peak; all values about equally frequent

Real data are rarely exactly symmetric or exactly uniform, so "approximately" or "roughly" belongs in most shape statements. See skewed left vs skewed right.

Which summary statistics to use

DistributionCenterVariability
Roughly symmetric, no outliersMeanStandard deviation
Skewed, or has outliersMedianIQR

The choice follows from resistance. A resistant statistic changes little when an outlier is added.

StatisticMeasuresFormula or definitionResistant to outliers
Mean xˉ\bar{x}Centerxˉ=∑xin\bar{x} = \frac{\sum x_i}{n}No
MedianCenterMiddle value of the ordered data, or the average of the two middle valuesYes
RangeVariabilitymax−min\text{max} - \text{min}No
IQRVariabilityQ3−Q1Q_3 - Q_1Yes
Standard deviation ssVariabilitys=∑(xi−xˉ)2n−1s = \sqrt{\frac{\sum (x_i - \bar{x})^2}{n - 1}}No

Q1Q_1 is the median of the lower half of the ordered data and Q3Q_3 is the median of the upper half. This site leaves the overall median out of both halves when nn is odd, which matches the TI-84. The range is a single number, so write "the range is 29 minutes", and give the minimum and maximum separately if they are wanted. See mean vs median.

Outlier rules

RuleA value is an outlier if it is
1.5×IQR1.5 \times \text{IQR} ruleLess than Q1−1.5(IQR)Q_1 - 1.5(\text{IQR}) or greater than Q3+1.5(IQR)Q_3 + 1.5(\text{IQR})
2 standard deviation ruleMore than 2 standard deviations above or below the mean

State which rule is being used and show the cutoff values. The two rules can disagree on the same data set.

A modified boxplot draws each whisker to the most extreme value that is not an outlier and marks each outlier with its own symbol. Worked cutoffs are in the 1.5 IQR rule.

Comparison sentence patterns

A comparison uses a comparative word (higher, lower, more variable, less variable), the same statistic for both groups, the values, and the context.

FeatureSentence pattern
Center"The median [variable] for [group A], [value with units], is higher than the median for [group B], [value with units]."
Variability"[Variable] varies more for [group A] than for [group B]: the IQRs are [value] and [value] [units]."
Shape"The distribution for [group A] is skewed right, while the distribution for [group B] is roughly symmetric."
Unusual features"[Group A] has a high outlier at [value with units]; [group B] has no outliers."

Two separate descriptions placed side by side are not a comparison. A comparison says which group is higher or more variable.

To compare individual values from different distributions, standardize each one: z=x−μσz = \frac{x - \mu}{\sigma}, the number of standard deviations the value lies above or below its own mean. The larger z-score marks the higher relative position. See how to compare two distributions.

What each graph shows

GraphShowsDoes not show
DotplotEvery value, shape, gaps, clusters, outliersNothing is hidden, but it is crowded for large data sets
StemplotEvery value, shape, gaps, clusters, outliersNothing is hidden, but it is crowded for large data sets
HistogramShape, gaps, clusters, and possible outliers by intervalIndividual values within an interval
BoxplotMedian, quartiles, IQR, range, outliers (if modified), skewness or symmetryGaps, clusters, and the number of peaks

A boxplot is built from the five-number summary: minimum, Q1Q_1, median, Q3Q_3, maximum. Each of its four sections holds about 25% of the data, so a longer section means the values there are more spread out, and it does not mean there are more values. See histogram vs boxplot.

Summarize and describe a small data set

The commute times, in minutes, of 9 employees are 12, 15, 16, 18, 19, 21, 22, 24, and 41. Find the five-number summary, check for outliers with both rules, and choose statistics to describe the distribution.

  1. Median: with 9 ordered values the median is the 5th value, 19 minutes.

  2. Quartiles: the lower half is 12, 15, 16, 18, so Q1=15+162=15.5Q_1 = \frac{15 + 16}{2} = 15.5. The upper half is 21, 22, 24, 41, so Q3=22+242=23Q_3 = \frac{22 + 24}{2} = 23.

  3. Five-number summary: 12, 15.5, 19, 23, 41. The IQR is 23−15.5=7.523 - 15.5 = 7.5 minutes.

  4. 1.5×IQR1.5 \times \text{IQR} rule: 1.5(7.5)=11.251.5(7.5) = 11.25. The cutoffs are 15.5−11.25=4.2515.5 - 11.25 = 4.25 and 23+11.25=34.2523 + 11.25 = 34.25. The value 41 is above 34.25, so it is an outlier.

  5. Mean: the values sum to 188, so xˉ=1889=20.89\bar{x} = \frac{188}{9} = 20.89 minutes.

  6. Standard deviation: the squared deviations from the mean sum to 564.89, so s=564.898=70.61=8.40s = \sqrt{\frac{564.89}{8}} = \sqrt{70.61} = 8.40 minutes.

  7. 2 standard deviation rule: 20.89+2(8.40)=37.6920.89 + 2(8.40) = 37.69 and 20.89−2(8.40)=4.0920.89 - 2(8.40) = 4.09. The value 41 is above 37.69, so this rule also flags it.

  8. The outlier pulls the mean (20.89) above the median (19) and inflates the standard deviation, so report the median and IQR.

Five-number summary: 12, 15.5, 19, 23, 41 minutes. The commute times have a median of 19 minutes and an IQR of 7.5 minutes, with most values between 12 and 24 minutes and one high outlier at 41 minutes.

Compare two values with z-scores

A student scores 82 on test A, where the class mean is 74 and the standard deviation is 8. The same student scores 70 on test B, where the class mean is 61 and the standard deviation is 6. On which test did the student do better relative to the class?

  1. Test A: z=82−748=88=1.0z = \frac{82 - 74}{8} = \frac{8}{8} = 1.0.

  2. Test B: z=70−616=96=1.5z = \frac{70 - 61}{6} = \frac{9}{6} = 1.5.

  3. Compare: 1.5 is greater than 1.0.

Test B. The score of 70 is 1.5 standard deviations above its class mean, while the score of 82 is 1.0 standard deviation above its class mean.

Frequently asked questions

Should I report the mean or the median?

Report the mean and standard deviation when the distribution is roughly symmetric with no outliers. Report the median and IQR when it is skewed or has outliers, because those two statistics are resistant. Pair the mean with the standard deviation and the median with the IQR.

How do I read skew from a boxplot?

A longer whisker on the right, or a median closer to the left side of the box, suggests right skew. The reverse suggests left skew. A boxplot cannot show gaps, clusters, or a second peak, so check a dotplot or histogram when those matter.

Are resistant and robust the same thing?

In this course the two words are used as synonyms for a statistic that outliers barely change. The median and IQR are resistant. The mean, range, and standard deviation are not. See what is a resistant statistic.