Outlier Detection Examples in Statistics

Start with the recap, study the fully worked examples, then use the practice problems to check your understanding of Outlier Detection.

This page combines explanation, solved examples, and follow-up practice so you can move from recognition to confident problem-solving in Statistics.

Concept Recap

Outlier detection is the process of identifying data points that are unusually far from the rest of the dataset, using techniques like the IQR rule, z-scores, or visual inspection of box plots and scatter plots. These anomalous values may indicate measurement errors, data entry mistakes, or genuinely extreme observations.

Outliers are data points that don't fit the pattern. A 7-foot student in a class of average heights, or a \$10 million house in a neighborhood of \$300k homes. They may be errors or genuinely unusual.

Read the full concept explanation โ†’

How to Use These Examples

  • Read the first worked example with the solution open so the structure is clear.
  • Try the practice problems before revealing each solution.
  • Use the related concepts and background knowledge badges if you feel stuck.

What to Focus On

Core idea: Outlier Detection asks how a value or feature behaves inside the full distribution.

Common stuck point: Students often know a procedure related to outlier detection but skip the recognition step: Am I interpreting the whole distribution or a value position inside it, rather than just computing a single summary? That leads to a calculation or graph that looks reasonable but answers a different question.

Sense of Study hint: Ask: Am I interpreting the whole distribution or a value position inside it, rather than just computing a single summary?

Common Mistakes to Watch For

Before you work through the examples, skim the mistake guide so you know which shortcuts and sign errors to avoid.

Worked Examples

Example 1

medium
Data 2,4,5,6,8,9,252, 4, 5, 6, 8, 9, 25 has Q1=4,Q3=9Q_1=4, Q_3=9. Is 2525 an outlier by the IQR rule?

Answer

Yes\text{Yes}

First step

1
IQR=9โˆ’4=5IQR = 9 - 4 = 5.

See the full worked solution + why-it-works coaching

SetupKey insightWhy it worksCommon pitfallConnection

Unlock answer keys One Family plan โ€” every worked solution, all subjects

Example 2

hard
A normally distributed quality test has mean 100100, SD 1010. How likely is a true measurement above 130130, under the โˆฃzโˆฃ>3|z|>3 rule?

Example 3

easy
The data set is: 10, 12, 11, 13, 12, 14, 11, 50. Identify the outlier and explain how you know.

Example 4

medium
Test scores: 72, 75, 78, 80, 82, 85, 88, 90, 92, 95. A new student's score of 25 is added. How does this outlier affect the mean and median?

Practice Problems

Try these problems on your own first, then open the solution to compare your method.

Example 1

easy
By the IQR rule, an outlier lies below Q1โˆ’1.5โ‹…IQRQ_1 - 1.5\cdot IQR or above which bound?

Example 2

easy
A data set has Q1=10Q_1 = 10 and Q3=20Q_3 = 20. Find the IQR.

Example 3

easy
With Q1=10Q_1=10, Q3=20Q_3=20, IQR=10IQR=10, find the lower fence Q1โˆ’1.5โ‹…IQRQ_1 - 1.5\cdot IQR.

Example 4

easy
With Q1=10Q_1=10, Q3=20Q_3=20, IQR=10IQR=10, find the upper fence Q3+1.5โ‹…IQRQ_3 + 1.5\cdot IQR.

Example 5

easy
Fences are โˆ’5-5 (lower) and 3535 (upper). Is the value 4040 an outlier?

Example 6

easy
Using z-scores, a common rule flags a value as an outlier when โˆฃzโˆฃ|z| exceeds what threshold?

Example 7

easy
Should you always delete an outlier as soon as you find one?

Example 8

easy
A box plot shows an isolated point far beyond the right whisker. What does it represent?

Example 9

medium
Data: 3,5,7,8,9,12,503, 5, 7, 8, 9, 12, 50 has Q1=5Q_1=5, Q3=12Q_3=12. Is 5050 an outlier by the IQR rule?

Example 10

medium
Data with Q1=20Q_1=20, Q3=40Q_3=40. What are both IQR-rule fences?

Example 11

medium
A value is 88, the mean is 2020, and the SD is 44. Is it an outlier by the โˆฃzโˆฃ>3|z|>3 rule?

Example 12

medium
Data: 1,2,2,3,3,3,4,1001, 2, 2, 3, 3, 3, 4, 100. Which value is the obvious outlier and why?

Example 13

medium
An outlier of 100100 is removed from a small data set. What happens to the mean and the SD?

Example 14

medium
Why might using ONLY the z-score method miss outliers in a skewed data set?

Example 15

medium
Data: 5,6,7,8,95, 6, 7, 8, 9 with Q1=6Q_1=6, Q3=8Q_3=8. Is the maximum value 99 an outlier?

Example 16

medium
A scatter plot point sits far from an otherwise tight linear trend. What is it called and what might it indicate?

Example 17

medium
Data 4,6,8,10,124, 6, 8, 10, 12 has Q1=5Q_1=5, Q3=11Q_3=11. Are there any outliers by the IQR rule?

Example 18

challenge
Data: 2,4,6,8,10,12,14,162, 4, 6, 8, 10, 12, 14, 16 with Q1=5Q_1=5, Q3=13Q_3=13. Find both fences and state whether any value is an outlier.

Example 19

challenge
For data 10,12,14,16,18,20,10010, 12, 14, 16, 18, 20, 100 with Q1=12Q_1=12, Q3=20Q_3=20, show 100100 is an outlier and explain why the mean is a poor center here.

Example 20

challenge
Explain why the IQR rule is more robust to extreme values than the z-score rule (one concise reason).

Example 21

easy
A data set has Q1=30Q_1 = 30 and Q3=50Q_3 = 50. Find the IQR.

Example 22

easy
With Q1=30,Q3=50,IQR=20Q_1=30, Q_3=50, IQR=20, what is the upper fence?

Example 23

easy
With Q1=30,Q3=50,IQR=20Q_1=30, Q_3=50, IQR=20, what is the lower fence?

Example 24

easy
The mean is 5050, SD is 55. Compute the z-score for x=70x = 70.

Example 25

easy
True or false: outliers should always be removed before analysis.

Example 26

easy
Data: 4,5,6,7,8,9,1004, 5, 6, 7, 8, 9, 100. Which value is most likely an outlier?

Example 27

medium
A value has z-score โˆ’2.5-2.5 in a roughly normal distribution. By the โˆฃzโˆฃ>3|z|>3 rule, is it an outlier?

Example 28

medium
Data: {1,2,3,4,5,6,7,8,9,50}\{1, 2, 3, 4, 5, 6, 7, 8, 9, 50\}. Find Q1,Q3Q_1, Q_3, and check if 5050 is an outlier.

Example 29

medium
In a strongly right-skewed distribution, IQR-rule outliers tend to appear on which side more often?

Example 30

medium
For Q1=12,Q3=20Q_1 = 12, Q_3 = 20, is 3030 an outlier by the IQR rule?

Example 31

medium
A z-score is calculated as z=โˆ’3.4z = -3.4 for some value xx. What does that mean?

Example 32

medium
A box plot shows the median near the BOX bottom, a short lower whisker, and one point far above the upper whisker. Most likely shape and outliers?

Example 33

hard
Data {2,4,4,5,6,7,8,9,12}\{2, 4, 4, 5, 6, 7, 8, 9, 12\} has Q1=4,Q3=8Q_1 = 4, Q_3 = 8. Identify any IQR-rule outliers.

Example 34

hard
A teacher records 3030 students' typing speeds. A z-score โˆฃzโˆฃ>3|z| > 3 rule flags two values. What should the teacher do?

Example 35

hard
Why does the IQR rule generally identify FEWER outliers than the โˆฃzโˆฃ>3|z|>3 rule for skewed data?

Example 36

hard
With Q1=25,Q3=75Q_1=25, Q_3=75, find both IQR-rule fences.

Example 37

hard
A modified IQR rule uses fences at Q1โˆ’3โ‹…IQRQ_1 - 3\cdot IQR and Q3+3โ‹…IQRQ_3 + 3\cdot IQR. Compared to the standard 1.5โ‹…IQR1.5\cdot IQR rule, what does it flag?

Example 38

medium
For ages of attendees at a children's birthday party, the value 4242 appears next to a long list of values from 44 to 1010. Is 4242 likely an outlier?

Example 39

hard
For data {0.5,1,1.2,1.5,1.8,2,2.2,5}\{0.5, 1, 1.2, 1.5, 1.8, 2, 2.2, 5\} with Q1=1.1,Q3=2.1Q_1 = 1.1, Q_3 = 2.1, is 55 an outlier?

Example 40

challenge
A data set of 5050 values is symmetric and approximately normal with ฮผ=0,ฯƒ=1\mu = 0, \sigma = 1. Roughly how many values would you expect to be flagged by the โˆฃzโˆฃ>3|z|>3 rule?

Example 41

medium
A scientist records reaction times (ms): 245, 260, 255, 270, 250, 980, 265, 258. Use the 1.5ร—IQR1.5 \times IQR rule to determine if 980 is an outlier. Should it be removed from the analysis?

Example 42

hard
A data set has mean xห‰=100\bar{x} = 100 and standard deviation s=15s = 15. Using the z-score method, determine whether the values 60, 145, and 155 are outliers (using the threshold โˆฃzโˆฃ>2|z| > 2).

Background Knowledge

These ideas may be useful before you work through the harder examples.

stat interquartile rangestat z score