Skip to content
AP Statistics · Exploring One-Variable Data and Collecting Data

Skewness

Skewness appears in 42 reviewed AP Statistics questions and sits in Exploring One-Variable Data and Collecting Data. Below are worked examples showing exactly how the exam tests it, with the answer marked and every distractor explained.

How Skewness is tested

Example 1Easier
A box plot for the lengths of phone calls shows that the lower whisker is very short, the box is compact, but there is a very long upper whisker with several plotted outlier points above it. This pattern is most consistent with which description?
  1. AA uniform distribution with extreme values.
  2. BA right-skewed distribution with high-value outliers.Correct
  3. CA symmetric distribution with high variability in both tails.
  4. DA left-skewed distribution with outliers at the low end.

Why B is right

A compact box with a short lower whisker and a very long upper whisker with outlier points above it indicates that most calls are short (clustered at the low end) but some calls are extremely long. This is characteristic of a right-skewed distribution with high-value outliers.
Why the other 3 choices miss
A
A uniform distribution would show roughly equal bar heights in a histogram, translating to roughly equal whisker lengths in a box plot. The extreme asymmetry described does not match uniformity.
C
A symmetric distribution would show equal whisker lengths and balanced box proportions. The very asymmetric pattern described is inconsistent with symmetry.
D
Left skew would produce a long LOWER whisker and short upper whisker, the opposite of what is described.
Example 2Medium
In a right-skewed distribution, which ordering of measures of center is correct?
  1. AMode < Median < MeanCorrect
  2. BMean = Median = Mode
  3. CMean < Median < Mode
  4. DMedian < Mode < Mean

Why A is right

In a right-skewed (positively skewed) distribution, the mode is at the peak (usually the leftmost high point), the median is pulled right by the tail but is resistant, and the mean is pulled furthest to the right by the extreme high values. The general ordering is Mode < Median < Mean.
Why the other 3 choices miss
B
Mean = Median = Mode holds only for perfectly symmetric distributions. Right-skewed distributions are by definition asymmetric.
C
Mean < Median < Mode is the pattern for LEFT-skewed distributions, where the tail extends to the left and low values pull the mean downward.
D
Median < Mode < Mean is not the typical ordering for any standard skewed distribution. In right-skewed data, the mode is at the peak on the left, below both the median and mean.
Example 3Easier
A histogram of household incomes in a county is strongly right-skewed. The mean income is $72,000 and the median income is $55,000. A local politician claims that "the average household earns $72,000 per year." Why is this statement potentially misleading?
  1. AThe mean is always inaccurate for large data sets because rounding errors accumulate when many incomes are added together
  2. BThe politician should use the mode instead of the mean for income data
  3. CThe mean is pulled up by the high-income tail, so it overstates what a typical household earnsCorrect
  4. DHousehold income should be reported as a proportion, not a dollar amount

Why C is right

In a right-skewed distribution, the mean is pulled toward the tail by high-income earners, making it larger than the median. The median ($55,000) better represents the income of a typical household. Reporting the mean ($72,000) overstates what a typical household earns.
Why the other 3 choices miss
A
Incorrect because the mean is a mathematically precise calculation; it does not become inaccurate from accumulated rounding. The issue is that it is not representative of the typical value in skewed distributions.
B
Incorrect because the mode is rarely used as the primary measure of center for continuous data like income; the median is the appropriate resistant measure.
D
Incorrect because there is nothing wrong with reporting income as a dollar amount; the issue is the choice of the mean over the median as the summary statistic.

Studied alongside

Other concepts from Exploring One-Variable Data and Collecting Data.